1 citations · 1 across the 3 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs
Zixuan Weng, Haoqi He, Weifei Jin +2
Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires distinguishing harmfulness re…
cs.CR2026
CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
Weifei Jin, Xilong Wang, Wei Zou +2
Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully crafted injected prompts into…