Paper-Conference

Cut the Deadwood Out: Training-Free Backdoor Purification via Guided Module Substitution

Yao Tong

• Feb 20, 2025 • 1 min read

How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning

Yao Tong

• Sep 20, 2024 • 1 min read

The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline

Haonan Wang

• Mar 20, 2024 • 1 min read