NTU等联合提出A-MemGuard：为AI记忆上锁，投毒攻击成功率暴降95%
"防御框架" 相关文章
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models
A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning
Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning
Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments
Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
RobustRAG: A Unique Defense Framework Developed for Opposing Retrieval Corruption Attacks in Retrieval-Augmented Generation (RAG) Systems
