conftrace_

jailbreak defense

32 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (12) model safety (9) jailbreak attack (8) adversarial attack (6) safety alignment (6) adversarial learning (6) adversarial defense (5) activation steering (4) vision-language model (4) ai safety (4)

Papers

X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Jailbreak Attacks without Compromising Usability EMNLP 2025 A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models ACL 2024 Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions EMNLP 2024 BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment NeurIPS 2024 Defending Jailbreak Prompts via In-Context Adversarial Game EMNLP 2024 Protecting Your LLMs with Information Bottleneck NeurIPS 2024 What Makes and Breaks Safety Fine-tuning? A Mechanistic Study NeurIPS 2024