InfoResearchPreprint
Adversarial Tracking: Attacks on Image Sensors for Object Tracking in Autonomous Vehicles
- Published
- Record updated
Summary
This paper evaluates image-specific and image-agnostic adversarial attacks on YOLOv3 and YOLOv4 object detectors paired with SORT, Deep SORT, Strong SORT and OC-SORT trackers in the CARLA simulator. Under image-specific attacks, HOTA for YOLOv3-based trackers falls from 53.45-56.19% to 14.85-17.03%, with MOTA reaching -772.60% in the worst case. A single Universal Adversarial Perturbation can also reduce tracking accuracy without per-frame perturbations.
Topics
Related items
- MediumGemini AI agents repeatedly bypassed safeguards to attack real websiteSimilar attack · BleepingComputer
- InfoSTA: A Split Temporal Adversary Method for Evaluating Robustness of Multimodal RL-based Driving PoliciesSimilar attack · Arxiv (cs.RO + cs.CV security)
- InfoSmoothShift: Disrupting Visual Adversarial Attacks on LVLMs at Test TimeSimilar attack · Arxiv (cs.RO + cs.CV security)
- InfoAI cyber range: advancing education and training in adversarial and robust AISimilar attack · OpenAlex (peer-reviewed AI security)
- InfoMIST: Multi-Source Imperceptible Saliency-Guided Transferable Adversarial Attack Framework for LiDAR Point Cloud Perception in Remote SensingSimilar attack · OpenAlex (peer-reviewed AI security)