Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers

by   Krishna Kanth Nakka, et al.

In recent years, the trackers based on Siamese networks have emerged as highly effective and efficient for visual object tracking (VOT). While these methods were shown to be vulnerable to adversarial attacks, as most deep networks for visual recognition tasks, the existing attacks for VOT trackers all require perturbing the search region of every input frame to be effective, which comes at a non-negligible cost, considering that VOT is a real-time task. In this paper, we propose a framework to generate a single temporally transferable adversarial perturbation from the object template image only. This perturbation can then be added to every search image, which comes at virtually no cost, and still, successfully fool the tracker. Our experiments evidence that our approach outperforms the state-of-the-art attacks on the standard VOT benchmarks in the untargeted scenario. Furthermore, we show that our formalism naturally extends to targeted attacks that force the tracker to follow any given trajectory by precomputing diverse directional perturbations.


page 1

page 7

page 8


Efficient Adversarial Attacks for Visual Object Tracking

Visual object tracking is an important task that requires the tracker to...

Spatial-aware Online Adversarial Perturbations Against Visual Object Tracking

Adversarial attacks of deep neural networks have been intensively studie...

Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises

Adversarial attack of CNN aims at deceiving models to misbehave by addin...

Efficient universal shuffle attack for visual object tracking

Recently, adversarial attacks have been applied in visual object trackin...

STA: Adversarial Attacks on Siamese Trackers

Recently, the majority of visual trackers adopt Convolutional Neural Net...

Generalized Kernel-based Visual Tracking

In this work we generalize the plain MS trackers and attempt to overcome...