adversarial learning
A strategy in machine learning where a model is trained to withstand adversarial attacks, often by learning to differentiate between perturbed and original inputs.
- Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness
- Bilevel Optimization for Adversarial Learning Problems: Sharpness, Generation, and Beyond
- Computable universal online learning
- Consistency of the $k_n$-nearest neighbor rule under adaptive sampling
- DEAL: Diffusion Evolution Adversarial Learning for Sim-to-Real Transfer
- Out-of-Distribution Generalized Graph Anomaly Detection with Homophily-aware Environment Mixup
- Simple and Effective Specialized Representations for Fair Classifiers
- Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models