conftrace_

safety boundary

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

activation defense (1) neural activation (1) large language model (1) boundary-safe representation (1) jailbreak defense (1) jailbreak attack (1) bayesian optimization (1) harmful content (1) feature representation (1) representation learning (1)

Papers

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models ACL 2025 X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Jailbreak Attacks without Compromising Usability EMNLP 2025