Adversarial Learning
Adversarial learning studies model behavior under intentionally crafted input perturbations and the threat models that produce them. Practical work focuses on generating attacks (e.g., FGSM, PGD), hardening via adversarial training or certified defenses, and evaluating clean vs. robust accuracy across attack strengths.
Beating the Variability: How Adversarial Learning is Transforming ECG-Based Arrhythmia Detection
2025/02/15
Balancing Data Privacy and Utility in Trajectory Data: A Collaborative Adversarial Learning Approach
2025/02/14
Fighting the Future of Social Bots: How CALEB is Changing the Game
2025/01/13
PriFU: Smarter Privacy for AI Without the Adversarial Hassle
2025/01/01