1 citations · 1 across the 5 of their papers we have counts for
6 papers
Rethinking LLM Jailbreak Evaluation: Continuous Risk Landscapes Beyond Binary Outcomes
Yukai Zhou, Wenjie Wang
A binary success indicator is a natural representation for discriminative tasks such as image classification under adversarial perturbations, where each input is mapped to a single…
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…
Wasserstein Adversarial Examples on Univariant Time Series Data
Wenjie Wang, Li Xiong, Jian Lou
Adversarial examples are crafted by adding indistinguishable perturbations to normal examples in order to fool a well-trained deep learning model to misclassify. In the context of…