arXiv cs.CR·5d agoToward Responsible AI-Augmented Cyber Defense: Pattern Recognition, Defense-in-Depth, and the Case for Human-AI Collaboration#ai-defense#soc#defense-in-depthResearch
arXiv cs.CR·8d agoCASCADE Against Jailbreaks: Combination Across Stages with Controlled Attack-Defense Evaluation#jailbreak#llm-security#defense-in-depthAI safety & security
Palo Alto Unit 42·29d agoPerturbation Probing: A New Diagnostic for the Fragility of LLM Safety#defense-in-depth#interpretability#llm-safety1
