TroubleLLM: Align to Red Team Expert

no code implementations • 28 Feb 2024 • Zhuoer Xu, Jianping Zhang, Shiwen Cui, Changhua Meng, Weiqiang Wang

Not only are these methods labor-intensive and require large budget costs, but the controllability of test prompt generation is lacking for the specific testing domain of LLM applications.

Backpropagation Path Search On Adversarial Transferability

no code implementations • ICCV 2023 • Zhuoer Xu, Zhangxuan Gu, Jianping Zhang, Shiwen Cui, Changhua Meng, Weiqiang Wang

Transfer-based attackers craft adversarial examples against surrogate models and transfer them to victim models deployed in the black-box situation.

Bayesian Optimization

On the Robustness of Latent Diffusion Models

1 code implementation • 14 Jun 2023 • Jianping Zhang, Zhuoer Xu, Shiwen Cui, Changhua Meng, Weibin Wu, Michael R. Lyu

Therefore, in this paper, we aim to analyze the robustness of latent diffusion models more thoroughly.

Denoising Image Generation

A2: Efficient Automated Attacker for Boosting Adversarial Training

1 code implementation • 7 Oct 2022 • Zhuoer Xu, Guanghui Zhu, Changhua Meng, Shiwen Cui, ZhenZhe Ying, Weiqiang Wang, Ming Gu, Yihua Huang

In this paper, we propose an efficient automated attacker called A2 to boost AT by generating the optimal perturbations on-the-fly during training.

Adversarial Defense