Jiayou Lu — accepted AI-conference papers

2025

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

Shilin Lu, Zihan Zhou, Jiayou Lu, Yuanzhi Zhu, Adams Wai-Kin Kong

ICLR 2025poster

Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks during editing, posing significant challenges to copyright protection. In this work, we introduce W-Bench, the first compre…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2025

When and Where do Data Poisons Attack Textual Inversion?

Jeremy Styborski, Mingzhi Lyu, Jiayou Lu, Nupur Kapur, Adams Wai-Kin Kong

ICCV 2025poster

Poisoning attacks pose significant challenges to the robustness of diffusion models (DMs). In this paper, we systematically analyze when and where poisoning attacks textual inversion (TI), a widely used personalization technique for DMs. We first introduce Semantic Sensitivity Maps, a novel method f…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗