4 papers
JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring
Junjie Chu, Mingjie Li, Ziqing Yang +6
Accurately determining whether a jailbreak attempt has succeeded is a fundamental yet unresolved challenge. Existing evaluation methods rely on misaligned proxy indicators or naive…
Never compromise with vulnerabilities: a comprehensive survey on AI governance
Yuchu Jiang, Jian Zhao, Yuchen Yuan +64
The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, t…
The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
Rui Zhang, Yun Shen, Hongwei Li +5
Recent research highlights concerns about the trustworthiness of third-party Pre-Trained Language Models (PTLMs) due to potential backdoor attacks. These backdoored PTLMs, however,…
BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors
Chia-Yi Hsu, Yu-Lin Tsai, Yu Zhe +6
Task arithmetic in large-scale pre-trained models enables agile adaptation to diverse downstream tasks without extensive retraining. By leveraging task vectors (TVs), users can per…