Efficient Adversarial Attacks for Visual Object Tracking
Visual object tracking is an important task that requires the tracker to find the objects quickly and accurately. The existing state-ofthe-art object trackers, i.e., Siamese based trackers, use DNNs to attain high accuracy. However, the robustness of visual tracking models is seldom explored. In this paper, we analyze the weakness of object trackers based on the Siamese network and then extend adversarial examples to visual object tracking. We present an end-to-end network FAN (Fast Attack Network) that uses a novel drift loss combined with the embedded feature loss to attack the Siamese network based trackers. Under a single GPU, FAN is efficient in the training speed and has a strong attack performance. The FAN can generate an adversarial example at 10ms, achieve effective targeted attack (at least 40% drop rate on OTB) and untargeted attack (at least 70% drop rate on OTB).
Code (0)
등록된 구현이 없습니다.
Tasks
GPUObjectObject TrackingVisual Object TrackingVisual TrackingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
One-Shot Adversarial Attacks on Visual Tracking With Dual Attention
Almost all adversarial attacks in computer vision are aimed at pre-known object categories, which could be offline trained for generating perturbations. But as for visual object tracking, the tracked target categories ar…
Adversarial AttackObjectObject TrackingVisual Object Tracking+1LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
Visual object tracking plays a critical role in visual-based autonomous systems, as it aims to estimate the position and size of the object of interest within a live video. Despite significant progress made in this field…
ObjectObject TrackingVisual Object TrackingAdversarial Attack for RGB-Event based Visual Object Tracking
Visual object tracking is a crucial research topic in the fields of computer vision and multi-modal fusion. Among various approaches, robust visual tracking that combines RGB frames with Event streams has attracted incre…
Adversarial AttackObject TrackingVisual Object TrackingVisual TrackingFooling Detection Alone is Not Enough: Adversarial Attack against Multiple Object Tracking
Recent work in adversarial machine learning started to focus on the visual perception in autonomous driving and studied Adversarial Examples (AEs) for object detection models. However, in such visual perception pipeline …
Adversarial AttackAutonomous DrivingBIG-bench Machine LearningMultiple Object Tracking+4Fooling Detection Alone is Not Enough: First Adversarial Attack against Multiple Object Tracking
Recent work in adversarial machine learning started to focus on the visual perception in autonomous driving and studied Adversarial Examples (AEs) for object detection models. However, in such visual perception pipeline …
Adversarial AttackAutonomous DrivingBIG-bench Machine LearningMultiple Object Tracking+4