会员服务
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
Arxiv
0+阅读 · 6月15日
DoubtProbe: Black-Box Jailbreak Defense via Structural Verification and Semantic Auditing
Arxiv
0+阅读 · 6月15日
GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking
Arxiv
0+阅读 · 6月14日
Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework
Arxiv
0+阅读 · 6月15日
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech
Arxiv
0+阅读 · 6月8日
JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization
Arxiv
0+阅读 · 6月9日
Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
Arxiv
0+阅读 · 5月25日
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
Arxiv
0+阅读 · 4月14日
FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization
Arxiv
0+阅读 · 6月11日
MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models
Arxiv
0+阅读 · 6月5日
PLAGUE: Plug-and-play framework for Lifelong Adaptive Generation of Multi-turn Exploits
Arxiv
0+阅读 · 6月5日
Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
Arxiv
0+阅读 · 4月23日
Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps
Arxiv
0+阅读 · 6月8日
GuardNet: Ensemble Strategies of Shallow Neural Networks for Robust Prompt Injection and Jailbreak Detection
Arxiv
0+阅读 · 6月4日
EvoJail: Evolutionary Diverse Jailbreak Prompt Generation for Large Language Models
Arxiv
0+阅读 · 4月22日
参考链接
微信扫码咨询专知VIP会员
Top