OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation Paper • 2512.06589 • Published 4 days ago • 16
AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery Paper • 2505.21499 • Published May 27 • 2
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment Paper • 2505.21494 • Published May 27 • 8
AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models Paper • 2505.16211 • Published May 22 • 18
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems Paper • 2504.01990 • Published Mar 31 • 300