Author

Wenyuan Xu

h-index 5 View on Semantic Scholar

We have 2 of 16 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Chameleon: Backdoor Attacks With Restoration-Based Triggers Using Diffusion Models.

Chameleon is proposed, a backdoor attack framework that reformulates sample-specific trigger generation as the restoration of a salient masked region that achieves a 28.42% higher effective attack success rate (E-ASR) compared to the best baseline when averaged across all defenses.

Boyang Zhou, Yixin He, Xiaofu Chen et al. · IEEE Transactions on Neural... · 0 citations

2026

Patronus: Safeguarding Text-to-Image Models Against Adversarial Fine-Tuning

Text-to-image (T2I) models can be exploited to produce unsafe images. Existing safety measures, e.g., content moderation or model alignment, can be weakened by adversaries who attempt to restore unsafe generation through model fine-tuning. This paper presents Patronus, a defensive framework that improves T2I models’ re...

Xin-Feng Li, Sheng-Yuan Pang, Jialin Wu et al. · IEEE Transactions on Informa... · 0 citations