Differentiated Directional Intervention A Framework for Evading LLM Safety Alignment
"攻击成功率" 相关文章
HarmNet: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models
PLAGUE: Plug-and-play framework for Lifelong Adaptive Generation of Multi-turn Exploits
Imperceptible Jailbreaking against Large Language Models
NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
Dagger Behind Smile: Fool LLMs with a Happy Ending Story
DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
Defending LVLMs Against Vision Attacks through Partial-Perception Supervision
The Cost of Thinking: Increased Jailbreak Risk in Large Language Models
LLM Robustness Leaderboard v1 --Technical report
PromptArmor: Simple yet Effective Prompt Injection Defenses
Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack
AdvDGMs: Enhancing Adversarial Robustness in Tabular Machine Learning by Incorporating Constraint Repair Layers for Realistic and Domain-Specific Attack Generation
AI大模型新型噪声攻击曝光，可绕过最先进的后门检测
