会员服务
Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs
Arxiv
0+阅读 · 2月18日
Boundary Point Jailbreaking of Black-Box LLMs
Arxiv
0+阅读 · 2月18日
TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking
Arxiv
0+阅读 · 2月6日
Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
Arxiv
0+阅读 · 2月16日
Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs
Arxiv
0+阅读 · 2月6日
Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
Arxiv
0+阅读 · 2月12日
SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
Arxiv
0+阅读 · 2月7日
SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
Arxiv
0+阅读 · 2月6日
ShallowJail: Steering Jailbreaks against Large Language Models
Arxiv
0+阅读 · 2月6日
ShallowJail: Steering Jailbreaks against Large Language Models
Arxiv
0+阅读 · 2月13日
AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks
Arxiv
0+阅读 · 2月14日
Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs
Arxiv
0+阅读 · 2月9日
Boundary Point Jailbreaking of Black-Box LLMs
Arxiv
0+阅读 · 2月16日
Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs
Arxiv
0+阅读 · 2月5日
Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models
Arxiv
0+阅读 · 2月5日
参考链接
微信扫码咨询专知VIP会员
Top