ROAST: Risk-aware Outlier-exposure for Adversarial Selective Training of Anomaly Detectors Against Evasion Attacks
ROAST proposes risk-aware adversarial training for anomaly detectors in safety-critical domains, aiming to close the evasion-resistance gap in DNN protection layers.
Summary written by editorial AI · Source link below
arXiv:2603.26093v3 Announce Type: replace Abstract: Safety-critical domains like healthcare rely on deep neural networks (DNNs) for prediction, yet DNNs remain vulnerable to evasion attacks. Anomaly detectors (ADs) are widely used to protect DNNs, but conventional ADs are trained indiscriminately on benign data from all patients, overlooking physiological differences that introduce noise, degrade robustness, and reduce recall. In this paper, we propose ROAST, a novel risk-aware outlier exposure
Editorial Analysis
Anomaly detectors protecting safety-critical ML systems remain brittle against evasion; risk-aware training could improve resilience in regulated sectors like healthcare.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at arXiv Crypto & Security in a new tab.
More from the Research Desk
- 39 New Methods That Compromise Passkey Authentication3d
- Security Vulnerability in a Voting System3d
- Selfie-Capture Dynamics as an Auxiliary Signal Against Deepfakes and Injection Attacks for Mobile Identity Verification4d
- How Reliable Is the Multi-Input Heuristic for Bitcoin Address Clustering in Law Enforcement Contexts?4d
- Privacy Leakage in Federated Learning: Gradient-Based Client Identity Inference and Defenses for Inertial Sensing in Vehicular Edge Networks4d