1 citations · 1 across the 3 of their papers we have counts for
Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
Where Do LLMs Decide to Break the Rules? Mechanistic Localization of Prompt Injection Compliance
Rui Wen, Jiayang Liu, Zeyu Yang +2
When a prompt injection attack succeeds, a Large Language Model (LLM) abandons its assigned system role to comply with an adversarial instruction. While prior work has extensively…
cs.CR2026
Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
Chia-Yi Hsu, Chia-Mu Yu, Chun-Ying Huang +1
LLM-powered coding agents increasingly participate in software development workflows by generating code, selecting dependencies, and producing package installation commands. This c…
cs.CR2025
One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs
Yixin Tan, Zhe Yu, Rui Wen +1
Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, parti…