4 papers
How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions
Yukai Zhou, Feiyang Lu, Xiaokai Mao +2
Jailbreak attacks on large language models are usually evaluated by attacker-centric metrics such as attack success rate (ASR), yet an attack that breaks a model is not necessarily…
: Natural and Universal Adversarial Attacks on Prompt-based Language Models
Yue Xu, Wenjie Wang
Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks…
Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing
Chengyan Fu, Wenjie Wang
Randomized smoothing is the primary certified robustness method for accessing the robustness of deep learning models to adversarial perturbations in the l2-norm, by adding isotropi…
Don't Say No: Jailbreaking LLM by Suppressing Refusal
Yukai Zhou, Jian Lou, Zhijie Huang +3
Ensuring the safety alignment of Large Language Models (LLMs) is critical for generating responses consistent with human values. However, LLMs remain vulnerable to jailbreaking att…