Over the past decade,the landscape of cybersecurity has been increasingly shaped by the growing sophistication and frequency of malware attacks.Traditional detection techniques,while still in use,often fall short when...Over the past decade,the landscape of cybersecurity has been increasingly shaped by the growing sophistication and frequency of malware attacks.Traditional detection techniques,while still in use,often fall short when confronted with modern threats that use advanced evasion strategies.This systematic review critically examines recent developments in malware detection,with a particular emphasis on the role of artificial intelligence(AI)and machine learning(ML)in enhancing detection capabilities.Drawing on literature published between 2019 and 2025,this study reviews 105 peer-reviewed contributions from prominent digital libraries including IEEE Xplore,SpringerLink,ScienceDirect,and ACM Digital Library.In doing so,it explores the evolution of malware,evaluates detection methods,assesses the quality and limitations of widely used datasets,and identifies key challenges facing the field.Unlike existing surveys,this work offers a structured comparison of AI-driven frameworks and provides a detailed account of emerging techniques such as hybrid detection frameworks and image-based analysis.The findings indicate that AIbased models trained on diverse,high-quality datasets consistently outperform conventional methods,particularly when supported by feature engineering,explainable AI and a multi-faceted strategy.The review concludes by outlining future research directions,including the need for standardized datasets,enhanced adversarial robustness,and the integration of privacy-preserving mechanisms in malware detection systems.展开更多
Traditional chaotic maps struggle with narrow chaotic ranges and inefficiencies,limiting their use for lightweight,secure image encryption in resource-constrained Wireless Sensor Networks(WSNs).We propose the SPCM,a n...Traditional chaotic maps struggle with narrow chaotic ranges and inefficiencies,limiting their use for lightweight,secure image encryption in resource-constrained Wireless Sensor Networks(WSNs).We propose the SPCM,a novel one-dimensional discontinuous chaotic system integrating polynomial and sine functions,leveraging a piecewise function to achieve a broad chaotic range()and a high Lyapunov exponent(5.04).Validated through nine benchmarks,including standard randomness tests,Diehard tests,and Shannon entropy(3.883),SPCM demonstrates superior randomness and high sensitivity to initial conditions.Applied to image encryption,SPCM achieves 0.152582 s(39%faster than some techniques)and 433.42 KB/s throughput(134%higher than some techniques),setting new benchmarks for chaotic map-based methods in WSNs.Chaos-based permutation and exclusive or(XOR)diffusion yield near-zero correlation in encrypted images,ensuring strong resistance to Statistical Attacks(SA)and accurate recovery.SPCM also exhibits a strong avalanche effect(bit difference),making it an efficient,secure solution for WSNs in domains like healthcare and smart cities.展开更多
文摘Over the past decade,the landscape of cybersecurity has been increasingly shaped by the growing sophistication and frequency of malware attacks.Traditional detection techniques,while still in use,often fall short when confronted with modern threats that use advanced evasion strategies.This systematic review critically examines recent developments in malware detection,with a particular emphasis on the role of artificial intelligence(AI)and machine learning(ML)in enhancing detection capabilities.Drawing on literature published between 2019 and 2025,this study reviews 105 peer-reviewed contributions from prominent digital libraries including IEEE Xplore,SpringerLink,ScienceDirect,and ACM Digital Library.In doing so,it explores the evolution of malware,evaluates detection methods,assesses the quality and limitations of widely used datasets,and identifies key challenges facing the field.Unlike existing surveys,this work offers a structured comparison of AI-driven frameworks and provides a detailed account of emerging techniques such as hybrid detection frameworks and image-based analysis.The findings indicate that AIbased models trained on diverse,high-quality datasets consistently outperform conventional methods,particularly when supported by feature engineering,explainable AI and a multi-faceted strategy.The review concludes by outlining future research directions,including the need for standardized datasets,enhanced adversarial robustness,and the integration of privacy-preserving mechanisms in malware detection systems.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korean government Ministry of Science and ICT(MIST)(RS-2022-00165225).
文摘Traditional chaotic maps struggle with narrow chaotic ranges and inefficiencies,limiting their use for lightweight,secure image encryption in resource-constrained Wireless Sensor Networks(WSNs).We propose the SPCM,a novel one-dimensional discontinuous chaotic system integrating polynomial and sine functions,leveraging a piecewise function to achieve a broad chaotic range()and a high Lyapunov exponent(5.04).Validated through nine benchmarks,including standard randomness tests,Diehard tests,and Shannon entropy(3.883),SPCM demonstrates superior randomness and high sensitivity to initial conditions.Applied to image encryption,SPCM achieves 0.152582 s(39%faster than some techniques)and 433.42 KB/s throughput(134%higher than some techniques),setting new benchmarks for chaotic map-based methods in WSNs.Chaos-based permutation and exclusive or(XOR)diffusion yield near-zero correlation in encrypted images,ensuring strong resistance to Statistical Attacks(SA)and accurate recovery.SPCM also exhibits a strong avalanche effect(bit difference),making it an efficient,secure solution for WSNs in domains like healthcare and smart cities.
