Semantic communication(SemCom)aims to achieve high-fidelity information delivery under low communication consumption by only guaranteeing semantic accuracy.Nevertheless,semantic communication still suffers from unexpe...Semantic communication(SemCom)aims to achieve high-fidelity information delivery under low communication consumption by only guaranteeing semantic accuracy.Nevertheless,semantic communication still suffers from unexpected channel volatility and thus developing a re-transmission mechanism(e.g.,hybrid automatic repeat request[HARQ])becomes indispensable.In that regard,instead of discarding previously transmitted information,the incremental knowledge-based HARQ(IK-HARQ)is deemed as a more effective mechanism that could sufficiently utilize the information semantics.However,considering the possible existence of semantic ambiguity in image transmission,a simple bit-level cyclic redundancy check(CRC)might compromise the performance of IK-HARQ.Therefore,there emerges a strong incentive to revolutionize the CRC mechanism,thus more effectively reaping the benefits of both SemCom and HARQ.In this paper,built on top of swin transformer-based joint source-channel coding(JSCC)and IK-HARQ,we propose a semantic image transmission framework SC-TDA-HARQ.In particular,different from the conventional CRC,we introduce a topological data analysis(TDA)-based error detection method,which capably digs out the inner topological and geometric information of images,to capture semantic information and determine the necessity for re-transmission.Extensive numerical results validate the effectiveness and efficiency of the proposed SC-TDA-HARQ framework,especially under the limited bandwidth condition,and manifest the superiority of TDA-based error detection method in image transmission.展开更多
The practical predictability of hail precipitation rates is significantly influenced by initial meteorological perturbations,stemming from various uncertainty sources.This study thoroughly assessed the predictability ...The practical predictability of hail precipitation rates is significantly influenced by initial meteorological perturbations,stemming from various uncertainty sources.This study thoroughly assessed the predictability of hail precipitation rates in both climatologically and flow-dependent perturbed ensembles(CEns and FEns).These ensembles incorporated initial meteorological uncertainties derived separately from two operational ensembles.Leveraging the Weather Research and Forecasting model,we conducted cloud-resolving simulations of an idealized hailstorm.The practical predictability of hail responded comparably to both climatological and flow-dependent uncertainties,which was revealed across the entire ensemble of 50 members.However,a notable difference emerged when comparing the peak hail precipitation rates among the top 10 and bottom 10 members.From a thermodynamic perspective,the primary source of uncertainty in hail precipitation lay in the significant variations in temperature stratification,particularly at-20℃and-40℃.On the microphysical front,perturbations within CEns generated greater uncertainty in the process of rainwater collection by hail,contributing significantly to the microphysical growth mechanisms of hail.Furthermore,the findings reveal a stronger dependency of hail precipitation uncertainty on thermodynamic perturbations compared to kinematic perturbations.These insights enhance the comprehension of the practical predictability of hail and contribute significantly to the understanding of ensemble forecasting for hail events.展开更多
Objective:Diabetic retinopathy(DR)screening using artificial intelligence(AI)has evolved significantly over the past decade.This study aimed to analyze research trends,developments,and patterns in AI-based fundus imag...Objective:Diabetic retinopathy(DR)screening using artificial intelligence(AI)has evolved significantly over the past decade.This study aimed to analyze research trends,developments,and patterns in AI-based fundus image DR screening from 2014 to 2024 through bibliometric analysis.Methods:The study used CiteSpace and Microsoft Excel to analyze 1,172 publications from the Web of Science Core Collection database.The analysis included publication trends over time,citation patterns,institutional collaborations,and the emergence of keywords.Results:From 2014-2022,there was a steady increase in the number of publications,reaching a peak in 2021.India(26%),China(20.05%),and the USA(9.98%)were the major contributors to research output in this field.Among the publication venues,IEEE ACCESS stood out as the leading one,with 44 articles published.The research landscape has evolved from traditional image processing techniques to deep learning approaches.In recent years,there has been a growing emphasis on multimodal AI models.The analysis identified three distinct phases in the development of AI-based DR screening:CNN-based systems(2014-2020),Vision Transformers and innovative learning paradigms(2020-2022),and large foundation models(2022-2024).Conclusions:The field has demonstrated a mature development in traditional AI approaches and is currently in the process of transitioning toward multimodal learning technologies.Future directions suggest an increased focus on the integration of telemedicine,innovative AI algorithms,and real-world implementation of these technologies in real-world settings.展开更多
Objective:Diabetic retinopathy(DR)is a top leading cause of blindness worldwide,requiring early detection for timely intervention.Artificial intelligence(AI)has emerged as a promising tool to improve DR screening effi...Objective:Diabetic retinopathy(DR)is a top leading cause of blindness worldwide,requiring early detection for timely intervention.Artificial intelligence(AI)has emerged as a promising tool to improve DR screening efficiency,accessibility,and cost-effectiveness.This study conducted a systematic review of literature and meta-analysis on the economic outcomes of AI-based DR screening.Methods:A systematic review of studies published before September 2024 was conducted throughout PubMed,Scopus,Embase,the Cochrane Library,the National Health Service Economic Evaluation Database,and the Cost-Effectiveness Analysis Registry.Eligible studies were included if they were(1)conducted among type 1 diabetes mellitus or type 2 diabetes mellitus adult diabetic population;(2)studies compared AI-based DR screening strategy to non-AI screening;and(3)performed a cost-effectiveness analysis.Meta-analysis was applied to pool incremental net benefit(INB)across studies stratified by country income and study perspective using a random-effects model.Statistical heterogeneity among studies was assessed using the I2 statistic,Cochrane Q statistics,and meta regression.Results:Nine studies were included in the analysis.From a healthcare system/payer perspective,AI-based DR screening was significantly cost-effective compared to non-AI-based screening,with a pooled INB of 615.77(95%confidence interval[CI]:558.27-673.27).Subgroup analysis showed robust cost-effectiveness of AI-based DR screening in high-income countries(INB=613.62,95%CI:556.06-671.18)and upper-/lower-middle income countries(INB=1,739.97,95%CI:423.13-3,056.82)with low heterogeneity.From a societal perspective,AI-based DR screening was generally cost-effective(INB=5,102.33,95%CI:-815.47-11,020.13),though the result lacked statistical significance and showed high heterogeneity.Conclusions:AI-based DR screening is generally cost-effective from a healthcare system perspective,particularly in high-income countries.Heterogeneity in cost-effectiveness across different perspectives highlights the importance of context-specific evaluations,to accurately evaluate the potential of AI-based DR screening in reducing global healthcare disparities.展开更多
Social Internet of Vehicles(SIoV)falls under the umbrella of social Internet of Things(IoT),where vehicles are socially connected to other vehicles and roadside units that can reliably share information and services w...Social Internet of Vehicles(SIoV)falls under the umbrella of social Internet of Things(IoT),where vehicles are socially connected to other vehicles and roadside units that can reliably share information and services with other social entities by leveraging the capabilities of 5G technology,which brings new opportunities and challenges,e.g.,collaborative power trading can address the mileage anxiety of electric vehicles.However,it relies on a trusted central party for scheduling,which introduces performance bottlenecks and cannot be set up in a distributed network,in addition,the lack of transparency in state-of-the-art Vehicle-to-Vehicle(V2V)power trading schemes can introduce further trust issues.In this paper,we propose a blockchain-based trustworthy collaborative power trading scheme for 5G-enabled social vehicular networks that uses a distributed market mechanism to introduce trusted power trading and avoids the dependence on a centralized dispatch center.Based on the game theory,we design the pricing and trading matching mechanism for V2V power trading to obtain maximum social welfare.We use blockchain to record power trading data for trusted pricing and use smart contracts for transaction matching.The simulation results verify the effectiveness of the proposed scheme in improving social welfare and reducing the load on the grid.展开更多
With the rapid advancement of cloud computing,cloud storage services have developed rapidly.One issue that has attracted particular attention in such remote storage services is that cloud storage servers are not enoug...With the rapid advancement of cloud computing,cloud storage services have developed rapidly.One issue that has attracted particular attention in such remote storage services is that cloud storage servers are not enough to reliably save and maintain data,which greatly affects users’confidence in purchasing and consuming cloud storage services.Traditional data integrity auditing techniques for cloud data storage are centralized,which faces huge security risks due to single-point-of-failure and vulnerabilities of central auditing servers.Blockchain technology offers a new approach to this problem.Many researchers have endeavored to employ the blockchain for data integrity auditing.Based on the search of relevant papers,we found that existing literature lacks a thorough survey of blockchain-based integrity auditing for cloud data.In this paper,we make an in-depth survey on cloud data integrity auditing based on blockchain.Firstly,we cover essential basic knowledge of integrity auditing for cloud data and blockchain techniques.Then,we propose a series of requirements for evaluating existing Blockchain-based Data Integrity Auditing(BDIA)schemes.Furthermore,we provide a comprehensive review of existing BDIA schemes and evaluate them based on our proposed criteria.Finally,according to our completed review and analysis,we explore some open issues and suggest research directions worthy of further efforts in the future.展开更多
With the rapid development of urban road traffic and the increasing number of vehicles,how to alleviate traffic congestion is one of the hot issues that need to be urgently addressed in building smart cities.Therefore...With the rapid development of urban road traffic and the increasing number of vehicles,how to alleviate traffic congestion is one of the hot issues that need to be urgently addressed in building smart cities.Therefore,in this paper,a nonlinear multi-objective optimization model of urban intersection signal timing based on a Genetic Algorithm was constructed.Specifically,a typical urban intersection was selected as the research object,and drivers’acceleration habits were taken into account.What’s more,the shortest average delay time,the least average number of stops,and the maximum capacity of the intersection were regarded as the optimization objectives.The optimization results show that compared with the Webster method when the vehicle speed is 60 km/h and the acceleration is 2.5 m/s^(2),the signal intersection timing scheme based on the proposed Genetic Algorithm multi-objective optimization reduces the intersection signal cycle time by 14.6%,the average vehicle delay time by 12.9%,the capacity by 16.2%,and the average number of vehicles stop by 0.4%.To verify the simulation results,the authors imported the optimized timing scheme into the constructed Simulation of the Urban Mobility model.The experimental results show that the authors optimized timing scheme is superior to Webster’s in terms of vehicle average loss time reduction,carbon monoxide emission,particulate matter emission,and vehicle fuel consumption.The research in this paper provides a basis for Genetic algorithms in traffic signal control.展开更多
Objective:To investigate the relationship between triterpenoid saponin content and antioxidant,antimicrobial,and α-glucosidase inhibitory activities of 70%ethanolic,butanolic,aqueous,supernate and precipitate extract...Objective:To investigate the relationship between triterpenoid saponin content and antioxidant,antimicrobial,and α-glucosidase inhibitory activities of 70%ethanolic,butanolic,aqueous,supernate and precipitate extracts of Juglans regia leaves.Methods:Triterpenoid saponins of different Juglans regia leaf extracts were measured by the vanillin method.Antioxidant activity was evaluated against DPPH and ABTS free radicals.We also assessed α-glucosidase inhibitory and antimicrobial activities of the leaf extracts.Pearson’s correlation coefficient was evaluated to determine the correlation between the saponin content and biological activities.Results:The butanolic extract was most effective against DPPH with an IC50of 6.63μg/mL,while the aqueous extract showed the highest scavenging activity against ABTS free radical with an IC50of 42.27μg/mL.Pearson’s correlation analysis indicated a strong negative correlation (r=-0.956) between DPPH radical scavenging activity (IC50) and the saponin content in the samples examined.In addition,the aqueous extract showed the best α-glucosidase inhibitory activity compared with other extracts.All the extracts had fair antibacterial activity against Bacillus subtilis,Escherichia coli,and Klebsiella pneumoniae except for the aqueous extract.Conclusions:Juglans regia extracts show potent antioxidant,antimicrobial,and α-glucosidase inhibitory activities.There is a correlation between saponin levels in Juglans regia leaf extracts and the studied activities.However,additional research is required to establish these relationships by identifying the specific saponin molecules responsible for these activities and elucidating their mechanisms of action.展开更多
Objective:To evaluate the prevalence and types of complementary and alternative medicine(CAM)modalities among patients with cancer in Karachi,Pakistan.Methods:This descriptive cross-sectional study was conducted from ...Objective:To evaluate the prevalence and types of complementary and alternative medicine(CAM)modalities among patients with cancer in Karachi,Pakistan.Methods:This descriptive cross-sectional study was conducted from March 2021 to December 2021.Five hundred patients with cancer were invited to participate in the study.Electronic databases,namely,Google scholar,Publons,EMBASE,PubMed,Chinese National Knowledge Infrastructure Database,and ResearchGate was used for questionnaire designed.The self-administered survey included questions on demographic characteristics,education level,socio-economic conditions and information about CAM therapies,prevalence,effectiveness,and common CAM modalities.Statistical analysis was conducted using SPSS software version 22.Results:Out of the 500 invited patients,433(86.6%)successfully completed and returned the questionnaires.In contrast to patients who were with younger,highly educated,professionally active,higher income,and had advanced cancer,time since diagnosis,type of treatment,cancer types and family history are significantly associated with CAM use.The results showed that 59.8%of the participants were acquainted with complementary and/or alternative medicine and considered safe owing to its natural ingredients.The prevalence of CAM usage among cancer patients was 40.9%and the most widely used CAM modality was herbal medicine(27.7%)and dietary supplements(28.8%).Patients used CAM as a complementary therapy to improve the morphological parameter(28.2%),strengthen the immune system(6.8%),and to decrease the side effects of conventional treatment(18.1%).Most of the respondents get the information regarding CAM therapy from the electronic media(43.2%)and the family members(48%)rather than healthcare personnel.Conclusions:Participants used CAM modalities along with the conventional health care practices.Further multicentre studies should be conducted to provide information regarding the usage of CAM therapies and their eventual benefits in patients with cancer.展开更多
With the maturity and development of 5G field,Mobile Edge CrowdSensing(MECS),as an intelligent data collection paradigm,provides a broad prospect for various applications in IoT.However,sensing users as data uploaders...With the maturity and development of 5G field,Mobile Edge CrowdSensing(MECS),as an intelligent data collection paradigm,provides a broad prospect for various applications in IoT.However,sensing users as data uploaders lack a balance between data benefits and privacy threats,leading to conservative data uploads and low revenue or excessive uploads and privacy breaches.To solve this problem,a Dynamic Privacy Measurement and Protection(DPMP)framework is proposed based on differential privacy and reinforcement learning.Firstly,a DPM model is designed to quantify the amount of data privacy,and a calculation method for personalized privacy threshold of different users is also designed.Furthermore,a Dynamic Private sensing data Selection(DPS)algorithm is proposed to help sensing users maximize data benefits within their privacy thresholds.Finally,theoretical analysis and ample experiment results show that DPMP framework is effective and efficient to achieve a balance between data benefits and sensing user privacy protection,in particular,the proposed DPMP framework has 63%and 23%higher training efficiency and data benefits,respectively,compared to the Monte Carlo algorithm.展开更多
Video analytics is an integral part of surveillance cameras. Comparedto video analytics, audio analytics offers several benefits, includingless expensive equipment and upkeep expenses. Additionally, the volume ofthe a...Video analytics is an integral part of surveillance cameras. Comparedto video analytics, audio analytics offers several benefits, includingless expensive equipment and upkeep expenses. Additionally, the volume ofthe audio datastream is substantially lower than the video camera datastream,especially concerning real-time operating systems, which makes it lessdemanding of the data channel’s bandwidth needs. For instance, automaticlive video streaming from the site of an explosion and gunshot to the policeconsole using audio analytics technologies would be exceedingly helpful forurban surveillance. Technologies for audio analytics may also be used toanalyze video recordings and identify occurrences. This research proposeda deep learning model based on the combination of convolutional neuralnetwork (CNN) and recurrent neural network (RNN) known as the CNNRNNapproach. The proposed model focused on automatically identifyingpulse sounds that indicate critical situations in audio sources. The algorithm’saccuracy ranged from 95% to 81% when classifying noises from incidents,including gunshots, explosions, shattered glass, sirens, cries, and dog barking.The proposed approach can be applied to provide security for citizens in openand closed locations, like stadiums, underground areas, shopping malls, andother places.展开更多
Objective:To assess the acute and subacute toxicity as well as the phytochemical composition of two extracts and three fractions of Ammi majus L.Methods:The aqueous extracts were prepared separately by maceration for ...Objective:To assess the acute and subacute toxicity as well as the phytochemical composition of two extracts and three fractions of Ammi majus L.Methods:The aqueous extracts were prepared separately by maceration for 48 h and by infusion for 1 h,while the fractions were prepared by the Soxhlet extractor,successively employing cyclohexane,ethyl acetate,and ethanol.The acute toxicity study was carried out in accordance with the OECD N°423 guideline at a single dose(2000 mg/kg)in mice for 14 days.The subacute toxicity study was performed by a daily oral administration of 250 mg/kg 2 for 10 d and 100 mg/kg doses for 28 d.Phytochemical screening was performed using staining and precipitation reactions,while the chemical characterization of some analytes was detected by HPLC-MS/MS analysis.Results:In the acute toxicity study,no signs of toxicity such as convulsion,salivation,diarrhea,sleep and coma were observed during 30 minutes and 14 days,so the lethal dose was higher than 2000 mg/kg for each extract and fraction.The subacute toxicity results showed that at a dose of 250 mg/kg,61.10%of the animals died and the rest developed morbidity.On the other hand,at a dose of 100 mg/kg,all the animals were still alive after 28 days,with no morbidity and the biochemical parameters were normal with no abnormalities in the liver,kidneys and pancreas.Phytochemical screening indicated the presence of flavonoids,tannins,coumarins,and free quinones and the absence of alkaloids and anthocyanins.Conclusions:The extracts and fractions of Ammi majus L.are not toxic in the short and long term with a varied chemical composition.Toxicological tests on animals other than rodents and in the long term(more than 28 days)are needed to further confirm the safety of Ammi majus extracts.展开更多
The development of society and the advancement of science and technology have led to the widespread integration of digital transformation in the field of education.However,the current establishment of green schools fa...The development of society and the advancement of science and technology have led to the widespread integration of digital transformation in the field of education.However,the current establishment of green schools faces various challenges,including non-environmental building facilities,high renovation costs,low organizational management efficiency,high energy consumption,outdated office tools,and insufficient environmental awareness among teachers and students.Through thorough research and analysis,it becomes evident that digital technology can play a pivotal role in addressing these challenges and contribute to all aspects of green school establishment.The incorporation of digital thinking concepts is essential for the construction of ecologically civilized campuses and inclusive innovation.The process of digital design and transformation proves instrumental in optimizing both software and hardware facilities within the campus,thereby reducing energy consumption.Simultaneously,comprehensive digital teaching management enhances overall efficiency in management and service delivery.Innovative digital teaching and learning models emerge as transformative tools,providing new avenues to create low-carbon,green classrooms for both teachers and students.By exploring the application of digital transformation in establishing green schools and examining the resulting spillover effects,valuable insights can be gained.These insights,in turn,serve as reference points for building diversified digital technology paths on campus and fostering the creation of green schools.展开更多
Along with the proliferating research interest in semantic communication(Sem Com),joint source channel coding(JSCC)has dominated the attention due to the widely assumed existence in efficiently delivering information ...Along with the proliferating research interest in semantic communication(Sem Com),joint source channel coding(JSCC)has dominated the attention due to the widely assumed existence in efficiently delivering information semantics.Nevertheless,this paper challenges the conventional JSCC paradigm and advocates for adopting separate source channel coding(SSCC)to enjoy a more underlying degree of freedom for optimization.We demonstrate that SSCC,after leveraging the strengths of the Large Language Model(LLM)for source coding and Error Correction Code Transformer(ECCT)complemented for channel coding,offers superior performance over JSCC.Our proposed framework also effectively highlights the compatibility challenges between Sem Com approaches and digital communication systems,particularly concerning the resource costs associated with the transmission of high-precision floating point numbers.Through comprehensive evaluations,we establish that assisted by LLM-based compression and ECCT-enhanced error correction,SSCC remains a viable and effective solution for modern communication systems.In other words,separate source channel coding is still what we need.展开更多
The advancement of 6G wireless communication technology has facilitated the integration of Vehicular Ad-hoc Networks(VANETs).However,the messages transmitted over the public channel in the open and dynamic VANETs are ...The advancement of 6G wireless communication technology has facilitated the integration of Vehicular Ad-hoc Networks(VANETs).However,the messages transmitted over the public channel in the open and dynamic VANETs are vulnerable to malicious attacks.Although numerous researchers have proposed authentication schemes to enhance the security of Vehicle-to-Vehicle(V2V)communication,most existing methodologies face two significant challenges:(1)the majority of the schemes are not lightweight enough to support realtime message interaction among vehicles;(2)the sensitive information like identity and position is at risk of being compromised.To tackle these issues,we propose a lightweight dual authentication protocol for V2V communication based on Physical Unclonable Function(PUF).The proposed scheme accomplishes dual authentication between vehicles by the combination of Zero-Knowledge Proof(ZKP)and MASK function.The security analysis proves that our scheme provides both anonymous authentication and information unlinkability.Additionally,the performance analysis demonstrates that the computation overhead of our scheme is approximately reduced 23.4% compared to the state-of-the-art schemes.The practical simulation conducted in a 6G network environment demonstrates the feasibility of 6G-based VANETs and their potential for future advancements.展开更多
Nirmal et al.presented a machine learning-based design of ternary organic solar cells,utilizing feature importance[1].This paper highlights the alarming potential biases in the use of feature importance in machine lea...Nirmal et al.presented a machine learning-based design of ternary organic solar cells,utilizing feature importance[1].This paper highlights the alarming potential biases in the use of feature importance in machine learning,which can lead to incorrect conclusions and outcomes.Many scientists and researchers including Nirmal et al.are unaware that feature importances in machine learning in general are model-specific and do not necessarily represent true associations between the target and features.展开更多
This paper presents a biosensor utilizing a whispering gallery mode(WGM)resonator characterized by azimuthal symmetry and crescent-shaped coatings of silver.The study investigates the impact of the coupling gap on the...This paper presents a biosensor utilizing a whispering gallery mode(WGM)resonator characterized by azimuthal symmetry and crescent-shaped coatings of silver.The study investigates the impact of the coupling gap on the extinction ratio and Q-factor of the setup.The resonator is coated with silver in crescent shapes,ranging from 40 nm to 65 nm in thickness.Coupling is achieved with a silica waveguide,simulating the tapered fiber coupling method.Notably,the resonator exhibits a maximum sensitivity of 220 nm/RIU when coated with 55-nm-thick silver in conjunction with a 4-nm-thick layer of thiol-tethered deoxyribonucleic acid(DNA).This biosensor holds promise for biomolecule detection applications.展开更多
The complexity of cloud environments challenges secure resource management,especially for intrusion detection systems(IDS).Existing strategies struggle to balance efficiency,cost fairness,and threat resilience.This pa...The complexity of cloud environments challenges secure resource management,especially for intrusion detection systems(IDS).Existing strategies struggle to balance efficiency,cost fairness,and threat resilience.This paper proposes an innovative approach to managing cloud resources through the integration of a genetic algorithm(GA)with a“double auction”method.This approach seeks to enhance security and efficiency by aligning buyers and sellers within an intelligent market framework.It guarantees equitable pricing while utilizing resources efficiently and optimizing advantages for all stakeholders.The GA functions as an intelligent search mechanism that identifies optimal combinations of bids from users and suppliers,addressing issues arising from the intricacies of cloud systems.Analyses proved that our method surpasses previous strategies,particularly in terms of price accuracy,speed,and the capacity to manage large-scale activities,critical factors for real-time cybersecurity systems,such as IDS.Our research integrates artificial intelligence-inspired evolutionary algorithms with market-driven methods to develop intelligent resource management systems that are secure,scalable,and adaptable to evolving risks,such as process innovation.展开更多
As smart contracts,represented by Solidity,become deeply integrated into the manufacturing industry,blockchain-based Digital Twins(DT)has gained momentum in recent years.Most of the blockchain infrastructures in wides...As smart contracts,represented by Solidity,become deeply integrated into the manufacturing industry,blockchain-based Digital Twins(DT)has gained momentum in recent years.Most of the blockchain infrastructures in widespread use today are based on the Proof-of-Work(PoW)mechanism,and the process of creating blocks is known as“mining”.Mining becomes increasingly difficult as the blockchain grows in size and the number of on-chain business systems increases.To lower the threshold of participation in the mining process,“mining pools”have been created.Miners can cooperate and share the mining rewards according to the hashrate they contributed to the pool.Stratum is the most widely used communication protocol between miners and mining pools.Its security is essential for the participants.In this paper,we propose two novel Man-In-The-Middle(MITM)attack schemes against Stratum,which allow attackers to steal miners'hashrate to any mining pool using hijacked TCP connections.Compared with existing attacks,our work is more secretive,more suitable for the real-world environment,and more harmful.The Proof-of-Concept(PoC)shows that our schemes work perfectly on most mining softwares and pools.Furthermore,we present a lightweight AI-driven approach based on protocol-level feature analysis to detect Stratum MITM for blockchain-based DTs.Its detection model consists of three layers:feature extraction layer,vectorization layer,and detection layer.Experiments prove that our detection approach can effectively detect Stratum MITM traffic with 98%accuracy.Our work alerts the communities and provides possible mitigation against these more hidden and profitable attack schemes.展开更多
基金supported in part by the National Key Research and Development Program of China under Grant 2024YFE0200600in part by the National Natural Science Foundation of China under Grant 62071425+3 种基金in part by the Zhejiang Key Research and Development Plan under Grant 2022C01093in part by the Zhejiang Provincial Natural Science Foundation of China under Grant LR23F010005in part by the National Key Laboratory of Wireless Communications Foundation under Grant 2023KP01601in part by the Big Data and Intelligent Computing Key Lab of CQUPT under Grant BDIC-2023-B-001.
文摘Semantic communication(SemCom)aims to achieve high-fidelity information delivery under low communication consumption by only guaranteeing semantic accuracy.Nevertheless,semantic communication still suffers from unexpected channel volatility and thus developing a re-transmission mechanism(e.g.,hybrid automatic repeat request[HARQ])becomes indispensable.In that regard,instead of discarding previously transmitted information,the incremental knowledge-based HARQ(IK-HARQ)is deemed as a more effective mechanism that could sufficiently utilize the information semantics.However,considering the possible existence of semantic ambiguity in image transmission,a simple bit-level cyclic redundancy check(CRC)might compromise the performance of IK-HARQ.Therefore,there emerges a strong incentive to revolutionize the CRC mechanism,thus more effectively reaping the benefits of both SemCom and HARQ.In this paper,built on top of swin transformer-based joint source-channel coding(JSCC)and IK-HARQ,we propose a semantic image transmission framework SC-TDA-HARQ.In particular,different from the conventional CRC,we introduce a topological data analysis(TDA)-based error detection method,which capably digs out the inner topological and geometric information of images,to capture semantic information and determine the necessity for re-transmission.Extensive numerical results validate the effectiveness and efficiency of the proposed SC-TDA-HARQ framework,especially under the limited bandwidth condition,and manifest the superiority of TDA-based error detection method in image transmission.
基金supported by the National Natural Science Foundation of China(Grant Nos.42005005 and 42030607)the Science and Technology Department of Shaanxi Province(Grant No.2024JC-YBQN-0248)+2 种基金the Education Department of Shaanxi Province(Grant No.23JK0686)a Xi'an Science and Technology Project(Grant No.22GXFW0131)the Young Talent fund of the University Association for Science and Technology in Shaanxi(Grant No.20210706)。
文摘The practical predictability of hail precipitation rates is significantly influenced by initial meteorological perturbations,stemming from various uncertainty sources.This study thoroughly assessed the predictability of hail precipitation rates in both climatologically and flow-dependent perturbed ensembles(CEns and FEns).These ensembles incorporated initial meteorological uncertainties derived separately from two operational ensembles.Leveraging the Weather Research and Forecasting model,we conducted cloud-resolving simulations of an idealized hailstorm.The practical predictability of hail responded comparably to both climatological and flow-dependent uncertainties,which was revealed across the entire ensemble of 50 members.However,a notable difference emerged when comparing the peak hail precipitation rates among the top 10 and bottom 10 members.From a thermodynamic perspective,the primary source of uncertainty in hail precipitation lay in the significant variations in temperature stratification,particularly at-20℃and-40℃.On the microphysical front,perturbations within CEns generated greater uncertainty in the process of rainwater collection by hail,contributing significantly to the microphysical growth mechanisms of hail.Furthermore,the findings reveal a stronger dependency of hail precipitation uncertainty on thermodynamic perturbations compared to kinematic perturbations.These insights enhance the comprehension of the practical predictability of hail and contribute significantly to the understanding of ensemble forecasting for hail events.
基金supported by the National Natural Science Foundation of China(62402009)the Science and Technology Development Fund of Macao(0013-2024-ITP1).
文摘Objective:Diabetic retinopathy(DR)screening using artificial intelligence(AI)has evolved significantly over the past decade.This study aimed to analyze research trends,developments,and patterns in AI-based fundus image DR screening from 2014 to 2024 through bibliometric analysis.Methods:The study used CiteSpace and Microsoft Excel to analyze 1,172 publications from the Web of Science Core Collection database.The analysis included publication trends over time,citation patterns,institutional collaborations,and the emergence of keywords.Results:From 2014-2022,there was a steady increase in the number of publications,reaching a peak in 2021.India(26%),China(20.05%),and the USA(9.98%)were the major contributors to research output in this field.Among the publication venues,IEEE ACCESS stood out as the leading one,with 44 articles published.The research landscape has evolved from traditional image processing techniques to deep learning approaches.In recent years,there has been a growing emphasis on multimodal AI models.The analysis identified three distinct phases in the development of AI-based DR screening:CNN-based systems(2014-2020),Vision Transformers and innovative learning paradigms(2020-2022),and large foundation models(2022-2024).Conclusions:The field has demonstrated a mature development in traditional AI approaches and is currently in the process of transitioning toward multimodal learning technologies.Future directions suggest an increased focus on the integration of telemedicine,innovative AI algorithms,and real-world implementation of these technologies in real-world settings.
基金supported by the Global STEM Professorship Scheme(P0046113)Henry G.Leong Endowed Professorship in Elderly Vision Health.
文摘Objective:Diabetic retinopathy(DR)is a top leading cause of blindness worldwide,requiring early detection for timely intervention.Artificial intelligence(AI)has emerged as a promising tool to improve DR screening efficiency,accessibility,and cost-effectiveness.This study conducted a systematic review of literature and meta-analysis on the economic outcomes of AI-based DR screening.Methods:A systematic review of studies published before September 2024 was conducted throughout PubMed,Scopus,Embase,the Cochrane Library,the National Health Service Economic Evaluation Database,and the Cost-Effectiveness Analysis Registry.Eligible studies were included if they were(1)conducted among type 1 diabetes mellitus or type 2 diabetes mellitus adult diabetic population;(2)studies compared AI-based DR screening strategy to non-AI screening;and(3)performed a cost-effectiveness analysis.Meta-analysis was applied to pool incremental net benefit(INB)across studies stratified by country income and study perspective using a random-effects model.Statistical heterogeneity among studies was assessed using the I2 statistic,Cochrane Q statistics,and meta regression.Results:Nine studies were included in the analysis.From a healthcare system/payer perspective,AI-based DR screening was significantly cost-effective compared to non-AI-based screening,with a pooled INB of 615.77(95%confidence interval[CI]:558.27-673.27).Subgroup analysis showed robust cost-effectiveness of AI-based DR screening in high-income countries(INB=613.62,95%CI:556.06-671.18)and upper-/lower-middle income countries(INB=1,739.97,95%CI:423.13-3,056.82)with low heterogeneity.From a societal perspective,AI-based DR screening was generally cost-effective(INB=5,102.33,95%CI:-815.47-11,020.13),though the result lacked statistical significance and showed high heterogeneity.Conclusions:AI-based DR screening is generally cost-effective from a healthcare system perspective,particularly in high-income countries.Heterogeneity in cost-effectiveness across different perspectives highlights the importance of context-specific evaluations,to accurately evaluate the potential of AI-based DR screening in reducing global healthcare disparities.
基金supported in part by the National Natural Science Foundation of China (No.62002113)the Natural Science Foundation of Hunan Province (No. 2021JJ40122).
文摘Social Internet of Vehicles(SIoV)falls under the umbrella of social Internet of Things(IoT),where vehicles are socially connected to other vehicles and roadside units that can reliably share information and services with other social entities by leveraging the capabilities of 5G technology,which brings new opportunities and challenges,e.g.,collaborative power trading can address the mileage anxiety of electric vehicles.However,it relies on a trusted central party for scheduling,which introduces performance bottlenecks and cannot be set up in a distributed network,in addition,the lack of transparency in state-of-the-art Vehicle-to-Vehicle(V2V)power trading schemes can introduce further trust issues.In this paper,we propose a blockchain-based trustworthy collaborative power trading scheme for 5G-enabled social vehicular networks that uses a distributed market mechanism to introduce trusted power trading and avoids the dependence on a centralized dispatch center.Based on the game theory,we design the pricing and trading matching mechanism for V2V power trading to obtain maximum social welfare.We use blockchain to record power trading data for trusted pricing and use smart contracts for transaction matching.The simulation results verify the effectiveness of the proposed scheme in improving social welfare and reducing the load on the grid.
基金This work was supported in part by the National Natural Science Foundation of China under Grant 62072351in part by the Academy of Finland under Grant 308087,Grant 335262,Grant 345072,and Grant 350464+1 种基金in part by the Open Project of Zhejiang Lab under Grant 2021PD0AB01and in part by the 111 Project under Grant B16037.
文摘With the rapid advancement of cloud computing,cloud storage services have developed rapidly.One issue that has attracted particular attention in such remote storage services is that cloud storage servers are not enough to reliably save and maintain data,which greatly affects users’confidence in purchasing and consuming cloud storage services.Traditional data integrity auditing techniques for cloud data storage are centralized,which faces huge security risks due to single-point-of-failure and vulnerabilities of central auditing servers.Blockchain technology offers a new approach to this problem.Many researchers have endeavored to employ the blockchain for data integrity auditing.Based on the search of relevant papers,we found that existing literature lacks a thorough survey of blockchain-based integrity auditing for cloud data.In this paper,we make an in-depth survey on cloud data integrity auditing based on blockchain.Firstly,we cover essential basic knowledge of integrity auditing for cloud data and blockchain techniques.Then,we propose a series of requirements for evaluating existing Blockchain-based Data Integrity Auditing(BDIA)schemes.Furthermore,we provide a comprehensive review of existing BDIA schemes and evaluate them based on our proposed criteria.Finally,according to our completed review and analysis,we explore some open issues and suggest research directions worthy of further efforts in the future.
基金supported by the joint NNSF&FDCT Project Number (0066/2019/AFJ)joint MOST&FDCT Project Number (0058/2019/AMJ),City University of Macao,Macao,China.
文摘With the rapid development of urban road traffic and the increasing number of vehicles,how to alleviate traffic congestion is one of the hot issues that need to be urgently addressed in building smart cities.Therefore,in this paper,a nonlinear multi-objective optimization model of urban intersection signal timing based on a Genetic Algorithm was constructed.Specifically,a typical urban intersection was selected as the research object,and drivers’acceleration habits were taken into account.What’s more,the shortest average delay time,the least average number of stops,and the maximum capacity of the intersection were regarded as the optimization objectives.The optimization results show that compared with the Webster method when the vehicle speed is 60 km/h and the acceleration is 2.5 m/s^(2),the signal intersection timing scheme based on the proposed Genetic Algorithm multi-objective optimization reduces the intersection signal cycle time by 14.6%,the average vehicle delay time by 12.9%,the capacity by 16.2%,and the average number of vehicles stop by 0.4%.To verify the simulation results,the authors imported the optimized timing scheme into the constructed Simulation of the Urban Mobility model.The experimental results show that the authors optimized timing scheme is superior to Webster’s in terms of vehicle average loss time reduction,carbon monoxide emission,particulate matter emission,and vehicle fuel consumption.The research in this paper provides a basis for Genetic algorithms in traffic signal control.
基金supported by the Deanship of Scientific Research at Umm Al-Qura University(Grant code:22UQU4331128DSR77).
文摘Objective:To investigate the relationship between triterpenoid saponin content and antioxidant,antimicrobial,and α-glucosidase inhibitory activities of 70%ethanolic,butanolic,aqueous,supernate and precipitate extracts of Juglans regia leaves.Methods:Triterpenoid saponins of different Juglans regia leaf extracts were measured by the vanillin method.Antioxidant activity was evaluated against DPPH and ABTS free radicals.We also assessed α-glucosidase inhibitory and antimicrobial activities of the leaf extracts.Pearson’s correlation coefficient was evaluated to determine the correlation between the saponin content and biological activities.Results:The butanolic extract was most effective against DPPH with an IC50of 6.63μg/mL,while the aqueous extract showed the highest scavenging activity against ABTS free radical with an IC50of 42.27μg/mL.Pearson’s correlation analysis indicated a strong negative correlation (r=-0.956) between DPPH radical scavenging activity (IC50) and the saponin content in the samples examined.In addition,the aqueous extract showed the best α-glucosidase inhibitory activity compared with other extracts.All the extracts had fair antibacterial activity against Bacillus subtilis,Escherichia coli,and Klebsiella pneumoniae except for the aqueous extract.Conclusions:Juglans regia extracts show potent antioxidant,antimicrobial,and α-glucosidase inhibitory activities.There is a correlation between saponin levels in Juglans regia leaf extracts and the studied activities.However,additional research is required to establish these relationships by identifying the specific saponin molecules responsible for these activities and elucidating their mechanisms of action.
文摘Objective:To evaluate the prevalence and types of complementary and alternative medicine(CAM)modalities among patients with cancer in Karachi,Pakistan.Methods:This descriptive cross-sectional study was conducted from March 2021 to December 2021.Five hundred patients with cancer were invited to participate in the study.Electronic databases,namely,Google scholar,Publons,EMBASE,PubMed,Chinese National Knowledge Infrastructure Database,and ResearchGate was used for questionnaire designed.The self-administered survey included questions on demographic characteristics,education level,socio-economic conditions and information about CAM therapies,prevalence,effectiveness,and common CAM modalities.Statistical analysis was conducted using SPSS software version 22.Results:Out of the 500 invited patients,433(86.6%)successfully completed and returned the questionnaires.In contrast to patients who were with younger,highly educated,professionally active,higher income,and had advanced cancer,time since diagnosis,type of treatment,cancer types and family history are significantly associated with CAM use.The results showed that 59.8%of the participants were acquainted with complementary and/or alternative medicine and considered safe owing to its natural ingredients.The prevalence of CAM usage among cancer patients was 40.9%and the most widely used CAM modality was herbal medicine(27.7%)and dietary supplements(28.8%).Patients used CAM as a complementary therapy to improve the morphological parameter(28.2%),strengthen the immune system(6.8%),and to decrease the side effects of conventional treatment(18.1%).Most of the respondents get the information regarding CAM therapy from the electronic media(43.2%)and the family members(48%)rather than healthcare personnel.Conclusions:Participants used CAM modalities along with the conventional health care practices.Further multicentre studies should be conducted to provide information regarding the usage of CAM therapies and their eventual benefits in patients with cancer.
基金supported in part by the National Natural Science Foundation of China under Grant U1905211,Grant 61872088,Grant 62072109,Grant 61872090,and Grant U1804263in part by the Guangxi Key Laboratory of Trusted Software under Grant KX202042+3 种基金in part by the Science and Technology Major Support Program of Guizhou Province under Grant 20183001in part by the Science and Technology Program of Guizhou Province under Grant 20191098in part by the Project of High-level Innovative Talents of Guizhou Province under Grant 20206008in part by the Open Research Fund of Key Laboratory of Cryptography of Zhejiang Province under Grant ZCL21015.
文摘With the maturity and development of 5G field,Mobile Edge CrowdSensing(MECS),as an intelligent data collection paradigm,provides a broad prospect for various applications in IoT.However,sensing users as data uploaders lack a balance between data benefits and privacy threats,leading to conservative data uploads and low revenue or excessive uploads and privacy breaches.To solve this problem,a Dynamic Privacy Measurement and Protection(DPMP)framework is proposed based on differential privacy and reinforcement learning.Firstly,a DPM model is designed to quantify the amount of data privacy,and a calculation method for personalized privacy threshold of different users is also designed.Furthermore,a Dynamic Private sensing data Selection(DPS)algorithm is proposed to help sensing users maximize data benefits within their privacy thresholds.Finally,theoretical analysis and ample experiment results show that DPMP framework is effective and efficient to achieve a balance between data benefits and sensing user privacy protection,in particular,the proposed DPMP framework has 63%and 23%higher training efficiency and data benefits,respectively,compared to the Monte Carlo algorithm.
基金funded by the project,“Design and implementation of real-time safety ensuring system in the indoor environment by applying machine learning techniques”.IRN:AP14971555.
文摘Video analytics is an integral part of surveillance cameras. Comparedto video analytics, audio analytics offers several benefits, includingless expensive equipment and upkeep expenses. Additionally, the volume ofthe audio datastream is substantially lower than the video camera datastream,especially concerning real-time operating systems, which makes it lessdemanding of the data channel’s bandwidth needs. For instance, automaticlive video streaming from the site of an explosion and gunshot to the policeconsole using audio analytics technologies would be exceedingly helpful forurban surveillance. Technologies for audio analytics may also be used toanalyze video recordings and identify occurrences. This research proposeda deep learning model based on the combination of convolutional neuralnetwork (CNN) and recurrent neural network (RNN) known as the CNNRNNapproach. The proposed model focused on automatically identifyingpulse sounds that indicate critical situations in audio sources. The algorithm’saccuracy ranged from 95% to 81% when classifying noises from incidents,including gunshots, explosions, shattered glass, sirens, cries, and dog barking.The proposed approach can be applied to provide security for citizens in openand closed locations, like stadiums, underground areas, shopping malls, andother places.
文摘Objective:To assess the acute and subacute toxicity as well as the phytochemical composition of two extracts and three fractions of Ammi majus L.Methods:The aqueous extracts were prepared separately by maceration for 48 h and by infusion for 1 h,while the fractions were prepared by the Soxhlet extractor,successively employing cyclohexane,ethyl acetate,and ethanol.The acute toxicity study was carried out in accordance with the OECD N°423 guideline at a single dose(2000 mg/kg)in mice for 14 days.The subacute toxicity study was performed by a daily oral administration of 250 mg/kg 2 for 10 d and 100 mg/kg doses for 28 d.Phytochemical screening was performed using staining and precipitation reactions,while the chemical characterization of some analytes was detected by HPLC-MS/MS analysis.Results:In the acute toxicity study,no signs of toxicity such as convulsion,salivation,diarrhea,sleep and coma were observed during 30 minutes and 14 days,so the lethal dose was higher than 2000 mg/kg for each extract and fraction.The subacute toxicity results showed that at a dose of 250 mg/kg,61.10%of the animals died and the rest developed morbidity.On the other hand,at a dose of 100 mg/kg,all the animals were still alive after 28 days,with no morbidity and the biochemical parameters were normal with no abnormalities in the liver,kidneys and pancreas.Phytochemical screening indicated the presence of flavonoids,tannins,coumarins,and free quinones and the absence of alkaloids and anthocyanins.Conclusions:The extracts and fractions of Ammi majus L.are not toxic in the short and long term with a varied chemical composition.Toxicological tests on animals other than rodents and in the long term(more than 28 days)are needed to further confirm the safety of Ammi majus extracts.
基金2022 School-Level Topic“Research on the Spillover Effects of Digital Transformation of Universities on Establishing Green Schools”(No.X2022094)。
文摘The development of society and the advancement of science and technology have led to the widespread integration of digital transformation in the field of education.However,the current establishment of green schools faces various challenges,including non-environmental building facilities,high renovation costs,low organizational management efficiency,high energy consumption,outdated office tools,and insufficient environmental awareness among teachers and students.Through thorough research and analysis,it becomes evident that digital technology can play a pivotal role in addressing these challenges and contribute to all aspects of green school establishment.The incorporation of digital thinking concepts is essential for the construction of ecologically civilized campuses and inclusive innovation.The process of digital design and transformation proves instrumental in optimizing both software and hardware facilities within the campus,thereby reducing energy consumption.Simultaneously,comprehensive digital teaching management enhances overall efficiency in management and service delivery.Innovative digital teaching and learning models emerge as transformative tools,providing new avenues to create low-carbon,green classrooms for both teachers and students.By exploring the application of digital transformation in establishing green schools and examining the resulting spillover effects,valuable insights can be gained.These insights,in turn,serve as reference points for building diversified digital technology paths on campus and fostering the creation of green schools.
基金supported in part by the National Key Research and Development Program of China under Grant No.2024YFE0200600the Zhejiang Provincial Natural Science Foundation of China under Grant No.LR23F010005the Huawei Cooperation Project under Grant No.TC20240829036。
文摘Along with the proliferating research interest in semantic communication(Sem Com),joint source channel coding(JSCC)has dominated the attention due to the widely assumed existence in efficiently delivering information semantics.Nevertheless,this paper challenges the conventional JSCC paradigm and advocates for adopting separate source channel coding(SSCC)to enjoy a more underlying degree of freedom for optimization.We demonstrate that SSCC,after leveraging the strengths of the Large Language Model(LLM)for source coding and Error Correction Code Transformer(ECCT)complemented for channel coding,offers superior performance over JSCC.Our proposed framework also effectively highlights the compatibility challenges between Sem Com approaches and digital communication systems,particularly concerning the resource costs associated with the transmission of high-precision floating point numbers.Through comprehensive evaluations,we establish that assisted by LLM-based compression and ECCT-enhanced error correction,SSCC remains a viable and effective solution for modern communication systems.In other words,separate source channel coding is still what we need.
文摘The advancement of 6G wireless communication technology has facilitated the integration of Vehicular Ad-hoc Networks(VANETs).However,the messages transmitted over the public channel in the open and dynamic VANETs are vulnerable to malicious attacks.Although numerous researchers have proposed authentication schemes to enhance the security of Vehicle-to-Vehicle(V2V)communication,most existing methodologies face two significant challenges:(1)the majority of the schemes are not lightweight enough to support realtime message interaction among vehicles;(2)the sensitive information like identity and position is at risk of being compromised.To tackle these issues,we propose a lightweight dual authentication protocol for V2V communication based on Physical Unclonable Function(PUF).The proposed scheme accomplishes dual authentication between vehicles by the combination of Zero-Knowledge Proof(ZKP)and MASK function.The security analysis proves that our scheme provides both anonymous authentication and information unlinkability.Additionally,the performance analysis demonstrates that the computation overhead of our scheme is approximately reduced 23.4% compared to the state-of-the-art schemes.The practical simulation conducted in a 6G network environment demonstrates the feasibility of 6G-based VANETs and their potential for future advancements.
文摘Nirmal et al.presented a machine learning-based design of ternary organic solar cells,utilizing feature importance[1].This paper highlights the alarming potential biases in the use of feature importance in machine learning,which can lead to incorrect conclusions and outcomes.Many scientists and researchers including Nirmal et al.are unaware that feature importances in machine learning in general are model-specific and do not necessarily represent true associations between the target and features.
基金supported by the Airlangga University through Mandate Research Grant(Nos.216/UN3.15/PT/2022 and 217/UN3.15/PT/2022)。
文摘This paper presents a biosensor utilizing a whispering gallery mode(WGM)resonator characterized by azimuthal symmetry and crescent-shaped coatings of silver.The study investigates the impact of the coupling gap on the extinction ratio and Q-factor of the setup.The resonator is coated with silver in crescent shapes,ranging from 40 nm to 65 nm in thickness.Coupling is achieved with a silica waveguide,simulating the tapered fiber coupling method.Notably,the resonator exhibits a maximum sensitivity of 220 nm/RIU when coated with 55-nm-thick silver in conjunction with a 4-nm-thick layer of thiol-tethered deoxyribonucleic acid(DNA).This biosensor holds promise for biomolecule detection applications.
文摘The complexity of cloud environments challenges secure resource management,especially for intrusion detection systems(IDS).Existing strategies struggle to balance efficiency,cost fairness,and threat resilience.This paper proposes an innovative approach to managing cloud resources through the integration of a genetic algorithm(GA)with a“double auction”method.This approach seeks to enhance security and efficiency by aligning buyers and sellers within an intelligent market framework.It guarantees equitable pricing while utilizing resources efficiently and optimizing advantages for all stakeholders.The GA functions as an intelligent search mechanism that identifies optimal combinations of bids from users and suppliers,addressing issues arising from the intricacies of cloud systems.Analyses proved that our method surpasses previous strategies,particularly in terms of price accuracy,speed,and the capacity to manage large-scale activities,critical factors for real-time cybersecurity systems,such as IDS.Our research integrates artificial intelligence-inspired evolutionary algorithms with market-driven methods to develop intelligent resource management systems that are secure,scalable,and adaptable to evolving risks,such as process innovation.
文摘As smart contracts,represented by Solidity,become deeply integrated into the manufacturing industry,blockchain-based Digital Twins(DT)has gained momentum in recent years.Most of the blockchain infrastructures in widespread use today are based on the Proof-of-Work(PoW)mechanism,and the process of creating blocks is known as“mining”.Mining becomes increasingly difficult as the blockchain grows in size and the number of on-chain business systems increases.To lower the threshold of participation in the mining process,“mining pools”have been created.Miners can cooperate and share the mining rewards according to the hashrate they contributed to the pool.Stratum is the most widely used communication protocol between miners and mining pools.Its security is essential for the participants.In this paper,we propose two novel Man-In-The-Middle(MITM)attack schemes against Stratum,which allow attackers to steal miners'hashrate to any mining pool using hijacked TCP connections.Compared with existing attacks,our work is more secretive,more suitable for the real-world environment,and more harmful.The Proof-of-Concept(PoC)shows that our schemes work perfectly on most mining softwares and pools.Furthermore,we present a lightweight AI-driven approach based on protocol-level feature analysis to detect Stratum MITM for blockchain-based DTs.Its detection model consists of three layers:feature extraction layer,vectorization layer,and detection layer.Experiments prove that our detection approach can effectively detect Stratum MITM traffic with 98%accuracy.Our work alerts the communities and provides possible mitigation against these more hidden and profitable attack schemes.
