Battista Biggio

Beyond Predictable Paths: Redefining AI Security Incident Reporting for Agents

Windows Malware Detector as a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness

EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability

Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation

DroidBreaker: Practical and Functional Problem-Space Attacks on Machine-Learning Android Malware Detectors

Latent-space Attacks for Refusal Evasion in Language Models

Label-efficient Training Updates for Malware Detection over Time

Evaluation of Audio Language Models for Fairness, Safety, and Security

BlackCATT: Black-box Collusion Aware Traitor Tracing in Federated Learning

SAGE-5GC: Security-Aware Guidelines for Evaluating Anomaly Detection in the 5G Core Network

Counterfeit Answers: Adversarial Forgery against OCR-Free Document Visual Question Answering

SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models