5 papers
Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite Moments
Qianqian Lei, Soham Bonnerjee, Yuefeng Han +1
While algorithmic stability is a central tool for understanding generalization of learning algorithms, existing high-probability guarantees typically rely on uniform boundedness or…
Data Reconstruction: Identifiability and Optimization with Sample Splitting
Yujie Shen, Zihan Wang, Jian Qian +1
Training data reconstruction from KKT conditions has shown striking empirical success, yet it remains unclear when the resulting KKT equations have unique solutions and, even in id…
Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection
Tianci Liu, Tong Yang, Quan Zhang +1
As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recen…
Data Reconstruction Attacks and Defenses: A Systematic Evaluation
Sheng Liu, Zihan Wang, Yuxiao Chen +1
Reconstruction attacks and defenses are essential in understanding the data leakage problem in machine learning. However, prior work has centered around empirical observations of g…
Elastic Representation: Mitigating Spurious Correlations for Group Robustness
Tao Wen, Zihan Wang, Quan Zhang +1
Deep learning models can suffer from severe performance degradation when relying on spurious correlations between input features and labels, making the models perform well on train…