3 papers
cs.CR2026
ROAST: Risk-aware Outlier-exposure for Adversarial Selective Training of Anomaly Detectors Against Evasion Attacks
Mohammed Elnawawy, Gargi Mitra, Shahrear Iqbal +1
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 t…
cs.CR2025
Systems-Theoretic and Data-Driven Security Analysis in ML-enabled Medical Devices
Gargi Mitra, Mohammadreza Hallajiyan, Inji Kim +5
The integration of AI/ML into medical devices is rapidly transforming healthcare by enhancing diagnostic and treatment facilities. However, this advancement also introduces serious…
cs.CR2025
Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs
Mohammed Elnawawy, Gargi Mitra, Shahrear Iqbal +1
Safety-critical applications such as healthcare and autonomous vehicles use deep neural networks (DNN) to make predictions and infer decisions. DNNs are susceptible to evasion atta…