2 papers
cs.LG2026
FlowPure: Continuous Normalizing Flows for Adversarial Purification
Elias Collaert, Abel RodrÃguez, Sander Joos +2
Despite significant advances in the area, adversarial robustness remains a critical challenge in systems employing machine learning models. The removal of adversarial perturbations…
cs.AI2025
The Adaptive Arms Race: Redefining Robustness in AI Security
Ilias Tsingenopoulos, Vera Rimmer, Davy Preuveneers +3
Despite considerable efforts on making them robust, real-world AI-based systems remain vulnerable to decision based attacks, as definitive proofs of their operational robustness ha…