Shengjie Zhou — accepted AI-conference papers

2025

Endowing Visual Reprogramming with Adversarial Robustness

Shengjie Zhou, Xin Cheng, Haiyang Xu, Ming Yan, Tao Xiang, Feng Liu +1

ICLR 2025poster

Visual reprogramming (VR) leverages well-developed pre-trained models (e.g., a pre-trained classifier on ImageNet) to tackle target tasks (e.g., a traffic sign recognition task), without the need for training from scratch. Despite the effectiveness of previous VR methods, all of them did not conside…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks

Shengjie Zhou, Lue Tao, Yuzhou Cao, Tao Xiang, Bo An, Lei Feng

ICLR 2024poster

Adversarial robustness is an important standard for measuring the quality of learned models, and adversarial training is an effective strategy for improving the adversarial robustness of models. In this paper, we disclose that adversarially trained models are vulnerable to two-faced attacks, where s…

Cited by 0 Source ↗PDF ↗Scholar ↗