Dual-verification-based model fingerprints against ambiguity attacks by Boyao Zhao, Haozhe Chen, Jie Zhang, Weiming Zhang, Nenghai Yu

Subjects: “…Model security…”
Get full text

Exploring the Limitations of Federated Learning: A Novel Wasserstein Metric-Based Poisoning Attack on Traffic Sign Classification by Suzan Almutairi, Ahmed Barnawi

Subjects: Get full text

Defending CNN Against FGSM Attacks Using Beta-Based Personalized Activation Functions and Adversarial Training by Hanen Issaoui, Asma Eladel, Ahmed Zouinkhi, Mourad Zaied, Lazhar Khriji, Sarvar Hussain Nengroo

Subjects: Get full text

A comprehensive analysis of model poisoning attacks in federated learning for autonomous vehicles: A benchmark study by Suzan Almutairi, Ahmed Barnawi

Subjects: Get full text

Research and application of defense mechanism for prompt injection attack of large language model in financial industry by MOU Daen, WEI Zhihua, SUN Minglong, SONG Na, NI Lin

Subjects: “…financial large language model security…”
Get full text

Application of fuzzy comprehensive evaluation method in network information security assessment of electric power enterprises by Daoyuan LIU, Keda SUN, Junliang ZHOU, Haidong FAN

Subjects: “…electric power enterprise;network information security model;security grade evaluation;comprehensive fuzzy evaluation method;secondary fuzzy comprehensive evaluation…”
Get full text