Skip to content

Author

Yahui Ding

2 papers indexed here

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.

#artificial intelligence Conference Aug 2025

DUP: Detection-guided Unlearning for Backdoor Purification in Language Models

DUP (Detection-guided Unlearning for Purification), a unified framework that integrates backdoor detection with unlearning-based purification, is proposed and innovatively repurpose knowledge distillation to guide the student model toward increasing its output divergence from the teacher on detected poisoned samples, e...

Man Hu, Ya-Hui Ding, Ya-Tao Yang et al. · 8 citations · ⚡1
Open access Aug 2026

Backdoor-free model watermarking via differential verification of adversarial samples and multi-bit information extraction

Model watermarking is a commonly used ownership verification technique for protecting the copyright of deep learning models. However, in practically deployed black-box model service scenarios, existing methods typically rely on misclassification-based backdoor trigger mechanisms, or assume that the verifier can obtain...

Jing Xiao, Song Xiao, Chao Guo et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.