Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
Faithful Dual-constrained Erasure for Robust LLM Safety Alignment
Jiaqing Li, Shide Zhou, Zhibo Zhang +3
Machine unlearning has emerged as a crucial mechanism for removing hazardous knowledge and enforcing safety alignment in Large Language Models (LLMs). However, recent studies revea…
cs.CR2026
RefineRAG: Word-Level Poisoning Attacks via Retriever-Guided Text Refinement
Ziye Wang, Guanyu Wang, Kailong Wang
Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs), but simultaneously exposes a critical vulnerability to knowledge poisoning attacks. Existi…
cs.CR2026
When Safe Models Merge into Danger: Exploiting Latent Vulnerabilities in LLM Fusion
Jiaqing Li, Zhibo Zhang, Shide Zhou +3
Model merging has emerged as a powerful technique for combining specialized capabilities from multiple fine-tuned LLMs without additional training costs. However, the security impl…