Yao Tong

3 papers · 2024–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze ❓ The Questioner

Venues

EMNLP (1) ICLR (1) ICML (1)

Top co-authors

Jiayuan Ye (1) Reza Shokri (1) Weijun Li (1) Haolan Zhan (1) Yang Zhang (1) Qianli Shen (1) Haonan Wang (1) Qiongkai Xu (1) Kenji Kawaguchi (1) Xuanli He (1)

Research topics

Machine Learning (3) Application Areas (2) Learning Types (2) Artificial Intelligence (1) Computer Vision (1) Deep Learning (1) Core AI (1) Generation (1) Models (1) Optimization & Theory (1)

Keywords

statistical learning (1) data poisoning (1) backdoor defense (1) model merging (1) machine learning (1) data privacy (1) backdoor attack (1) diffusion model (1) generative ai (1) membership inference (1) model purification (1) copyright infringement (1) text to image (1) module substitution (1) retraining-free defense (1) dataset usage (1) poisoning data (1)

Papers

Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution EMNLP 2025 How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning ICLR 2025 The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline ICML 2024