4 papers
AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification
Hongyi Cen, Mingxin Wang, Yule Liu +3
Large language models (LLMs) can rewrite refuted claims to evade evidence-based fact verifiers, but conventional attack success rate (ASR) can be inflated when rewrites change, wea…
StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
Huawei Zheng, Xinqi Jiang, Sen Yang +3
Large language models (LLMs) are increasingly applied in specialized domains such as finance and healthcare, where they introduce unique safety risks. Domain-specific datasets of h…
NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
Chuhan Zhang, Ye Zhang, Bowen Shi +5
In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jail…
CAMH: Advancing Model Hijacking Attack in Machine Learning
Xing He, Jiahao Chen, Yuwen Pu +5
In the burgeoning domain of machine learning, the reliance on third-party services for model training and the adoption of pre-trained models have surged. However, this reliance int…