Publications

(2027). Meta-VLM: Which Metadata Do Vision-Language Models Need to Drive Safely?. Winter Conference on Applications of Computer Vision (WACV'27).
(2027). User Perceptions of Deceptive In-Vehicle Infotainment User Interfaces. Network and Distributed System Security Symposium (NDSS'27).
(2026). Relational Feature Distillation for Lightweight 3D Point Cloud Segmentation. Annual Conference on Neural Information Processing Systems (NeurIPS'26).
(2026). On the Vulnerability of Lane Detectors to Physical Shadow. IEEE Annual Computer Security Applications Conference (ACSAC'26).
(2026). On the Quantum Advantage in Black-Box Adversarial Attacks. Annual Conference on Neural Information Processing Systems (NeurIPS'26).
(2026). LLMCluster: Fuzzing Crash Triage using Generative AI. International Symposium on Foundations & Practice of Security (FPS'26).
(2026). GATE: Reliability-Gated Gaussian Evidence Fusion for Training-Free Test-Time Adaptation of Vision-Language Models. British Machine Vision Conference (BMVC'26).
(2026). CANdy: Backward-Compatible CAN Message Authentication via Sub-Bit Injection on Commercial Controllers. International Symposium on Research in Attacks, Intrusions and Defenses (RAID'26).
(2026). Evaluating the Robustness of Segmentation Models against Adversarial Patches in Off-Road Environments. NDIA Ground Vehicle Systems Engineering & Technology Symposium (GVSETS'26).
(2026). Short: CARdea: Two-Phase Plausibility-Based Vehicle-to-Vehicle Anomaly Detection System. 4th USENIX Symposium on Vehicle Security and Privacy (VehicleSec).