The authors propose an informed search greedy approach that efficiently identifies the influencer nodes in the social Internet of Things with the ability to provide legitimate information.Primarily,the proposed approa...The authors propose an informed search greedy approach that efficiently identifies the influencer nodes in the social Internet of Things with the ability to provide legitimate information.Primarily,the proposed approach minimizes the network size and eliminates undesirable connections.For that,the proposed approach ranks each of the nodes and prioritizes them to identify an authentic influencer.Therefore,the proposed approach discards the nodes having a rank(α)lesser than 0.5 to reduce the network complexity.αis the variable value represents the rank of each node that varies between 0 to 1.Node with the higher value ofαgets the higher priority and vice versa.The threshold valueα=0.5 defined by the authors with respect to their network pruning requirements that can be vary with respect to other research problems.Finally,the algorithm in the proposed approach traverses the trimmed network to identify the authentic node to obtain the desired information.The performance of the proposed method is evaluated in terms of time complexity and accuracy by executing the algorithm on both the original and pruned networks.Experimental results show that the approach identifies authentic influencers on a resultant network in significantly less time than in the original network.Moreover,the accuracy of the proposed approach in identifying the influencer node is significantly higher than that of the original network.Furthermore,the comparison of the proposed approach with the existing approaches demonstrates its efficiency in terms of time consumption and network traversal through the minimum number of hops.展开更多
Recently,studies show that deep learning-based automatic speech recognition(ASR)systems are vulnerable to adversarial examples(AEs),which add a small amount of noise to the original audio examples.These AE attacks pos...Recently,studies show that deep learning-based automatic speech recognition(ASR)systems are vulnerable to adversarial examples(AEs),which add a small amount of noise to the original audio examples.These AE attacks pose new challenges to deep learning security and have raised significant concerns about deploying ASR systems and devices.The existing defense methods are either limited in application or only defend on results,but not on process.In this work,we propose a novel method to infer the adversary intent and discover audio adversarial examples based on the AEs generation process.The insight of this method is based on the observation:many existing audio AE attacks utilize query-based methods,which means the adversary must send continuous and similar queries to target ASR models during the audio AE generation process.Inspired by this observation,We propose a memory mechanism by adopting audio fingerprint technology to analyze the similarity of the current query with a certain length of memory query.Thus,we can identify when a sequence of queries appears to be suspectable to generate audio AEs.Through extensive evaluation on four state-of-the-art audio AE attacks,we demonstrate that on average our defense identify the adversary’s intent with over 90%accuracy.With careful regard for robustness evaluations,we also analyze our proposed defense and its strength to withstand two adaptive attacks.Finally,our scheme is available out-of-the-box and directly compatible with any ensemble of ASR defense models to uncover audio AE attacks effectively without model retraining.展开更多
基金This work was supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.2021R1A5A1021944 and 2021R1I1A3048013)Additionally,the research was supported by Kyungpook National University Research Fund,2020.
文摘The authors propose an informed search greedy approach that efficiently identifies the influencer nodes in the social Internet of Things with the ability to provide legitimate information.Primarily,the proposed approach minimizes the network size and eliminates undesirable connections.For that,the proposed approach ranks each of the nodes and prioritizes them to identify an authentic influencer.Therefore,the proposed approach discards the nodes having a rank(α)lesser than 0.5 to reduce the network complexity.αis the variable value represents the rank of each node that varies between 0 to 1.Node with the higher value ofαgets the higher priority and vice versa.The threshold valueα=0.5 defined by the authors with respect to their network pruning requirements that can be vary with respect to other research problems.Finally,the algorithm in the proposed approach traverses the trimmed network to identify the authentic node to obtain the desired information.The performance of the proposed method is evaluated in terms of time complexity and accuracy by executing the algorithm on both the original and pruned networks.Experimental results show that the approach identifies authentic influencers on a resultant network in significantly less time than in the original network.Moreover,the accuracy of the proposed approach in identifying the influencer node is significantly higher than that of the original network.Furthermore,the comparison of the proposed approach with the existing approaches demonstrates its efficiency in terms of time consumption and network traversal through the minimum number of hops.
基金supported in part by NSFC No.62202275,Shandong-SF No.ZR2022QF012 projects.
文摘Recently,studies show that deep learning-based automatic speech recognition(ASR)systems are vulnerable to adversarial examples(AEs),which add a small amount of noise to the original audio examples.These AE attacks pose new challenges to deep learning security and have raised significant concerns about deploying ASR systems and devices.The existing defense methods are either limited in application or only defend on results,but not on process.In this work,we propose a novel method to infer the adversary intent and discover audio adversarial examples based on the AEs generation process.The insight of this method is based on the observation:many existing audio AE attacks utilize query-based methods,which means the adversary must send continuous and similar queries to target ASR models during the audio AE generation process.Inspired by this observation,We propose a memory mechanism by adopting audio fingerprint technology to analyze the similarity of the current query with a certain length of memory query.Thus,we can identify when a sequence of queries appears to be suspectable to generate audio AEs.Through extensive evaluation on four state-of-the-art audio AE attacks,we demonstrate that on average our defense identify the adversary’s intent with over 90%accuracy.With careful regard for robustness evaluations,we also analyze our proposed defense and its strength to withstand two adaptive attacks.Finally,our scheme is available out-of-the-box and directly compatible with any ensemble of ASR defense models to uncover audio AE attacks effectively without model retraining.
