Results 61 to 70 of about 156,834 (158)
Adversarial Machine Learning for NextG Covert Communications Using Multiple Antennas. [PDF]
Entropy (Basel), 2022 Kim B +4 more
europepmc +1 more source
Adversarial Machine Learning: Perspectives from Adversarial Risk Analysis
, 2020 Adversarial Machine Learning (AML) is emerging as a major eld aimed at the protection of automated ML systems against security threats. The majority of work in this area has built upon a game-theoretic framework by modelling a conict between an attacker and a defender.
Insua, David Rios +3 more
openaire +1 more source
A Survey on Adversarial Attacks for Malware Analysis
IEEE AccessMachine learning-based malware analysis approaches are widely researched and deployed in critical infrastructures for detecting and classifying evasive and growing malware threats.
Kshitiz Aryal +4 more
doaj +1 more source
Enhancing quantum adversarial robustness by randomized encodings
Physical Review ResearchThe interplay between quantum physics and machine learning gives rise to the emergent frontier of quantum machine learning, where advanced quantum learning models may outperform their classical counterparts in solving certain challenging problems ...
Weiyuan Gong +3 more
doaj +1 more source
Multi-Stage Adversarial Defense for Online DDoS Attack Detection System in IoT
IEEE AccessMachine learning-based Distributed Denial of Service (DDoS) attack detection systems have proven effective in detecting and preventing DDoD attacks in Internet of Things (IoT) systems.
Yonas Kibret Beshah +2 more
doaj +1 more source
Adversarial Machine Learning at Scale
, 2016 17 pages, 5 ...
Kurakin, Alexey +2 more
openaire +2 more sources
A System-Driven Taxonomy of Attacks and Defenses in Adversarial Machine Learning. [PDF]
IEEE Trans Emerg Top Comput Intell, 2020 Sadeghi K, Banerjee A, Gupta SKS.
europepmc +1 more source
Adversarial Machine Learning and Cybersecurity
, 2023 Artificial intelligence systems are rapidly being deployed in all sectors of the economy, yet significant research has demonstrated that these systems can be vulnerable to a wide array of attacks. How different are these problems from more common cybersecurity vulnerabilities?
openaire +1 more source
Evasive attacks against autoencoder-based cyberattack detection systems in power systems
Energy and AIThe digital transformation process of power systems towards smart grids is resulting in improved reliability, efficiency and situational awareness at the expense of increased cybersecurity vulnerabilities. Given the availability of large volumes of smart
Yew Meng Khaw +3 more
doaj +1 more source