conftrace_

harmful information

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

malicious queries (1) safety-aligned llm (1) malicious retrieval (1) bias injection (1) misinformation injection (1) clipped-proximal policy optimization (1) image encoder layers (1) layer-wise ppo (1) knowledge erasure (1) instruction-following retriever (1)

Papers

Can Editing LLMs Inject Harm? AAAI 2026 Exploiting Instruction-Following Retrievers for Malicious Information Retrieval ACL 2025 Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models ICML 2025 UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets EMNLP 2025