🧪 Test?View on arXiv
Adversarial Tracking: Attacks on Image Sensors for Object Tracking in Autonomous Vehicles
Not specified in the provided content
adversarial attacksobject trackingautonomous vehicles
2611.17505
Builder Relevance
19h ago80%
Abstract
This paper evaluates the impact of adversarial attacks on object tracking systems in autonomous vehicles, specifically focusing on YOLOv3 and YOLOv4 detectors.
Reality Card
Core Claim
The study demonstrates that adversarial attacks significantly degrade the tracking accuracy of YOLOv3 and YOLOv4-based systems, with MOTA reaching as low as -772.60% under image-specific attacks.
Method / Result
Under image-specific attacks, HOTA for YOLOv3-based trackers declines from 53.45-56.19% to 14.85-17.03%.
Limitations
The paper does not specify the authors or provide detailed methodologies for reproducing the results.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.