Search Results for author:
Found 3 papers, 2 papers with code
Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning
Our research, initially spurred by test-time evasion attacks, investigates the intersection of adversarial training and backdoor attacks within federated learning, introducing Adversarial Robustness Unhardening (ARU).
Characterizing Internal Evasion Attacks in Federated Learning
However, combining adversarial training with personalized federated learning frameworks increases relative internal attack robustness by 60% compared to federated adversarial training and performs well under limited system resources.
Can we Generalize and Distribute Private Representation Learning?
We study the problem of learning representations that are private yet informative, i. e., provide information about intended "ally" targets while hiding sensitive "adversary" attributes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
