Boosting the Transferability of Video Adversarial Examples via Temporal Translation

by   Zhipeng Wei, et al.

Although deep-learning based video recognition models have achieved remarkable success, they are vulnerable to adversarial examples that are generated by adding human-imperceptible perturbations on clean video samples. As indicated in recent studies, adversarial examples are transferable, which makes it feasible for black-box attacks in real-world applications. Nevertheless, most existing adversarial attack methods have poor transferability when attacking other video models and transfer-based attacks on video models are still unexplored. To this end, we propose to boost the transferability of video adversarial examples for black-box attacks on video recognition models. Through extensive analysis, we discover that different video recognition models rely on different discriminative temporal patterns, leading to the poor transferability of video adversarial examples. This motivates us to introduce a temporal translation attack method, which optimizes the adversarial perturbations over a set of temporal translated video clips. By generating adversarial examples over translated videos, the resulting adversarial examples are less sensitive to temporal patterns existed in the white-box model being attacked and thus can be better transferred. Extensive experiments on the Kinetics-400 dataset and the UCF-101 dataset demonstrate that our method can significantly boost the transferability of video adversarial examples. For transfer-based attack against video recognition models, it achieves a 61.56 and 48.60


page 1

page 2

page 3

page 4


Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks

Deep neural networks are vulnerable to adversarial examples, which can m...

Cross-Modal Transferable Adversarial Attacks from Images to Videos

Recent studies have shown that adversarial examples hand-crafted on one ...

Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchy

The transferability and robustness of adversarial examples are two pract...

Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World

Deep learning models are vulnerable to adversarial examples. As a more t...

Improving the Transferability of Adversarial Examples with Restructure Embedded Patches

Vision transformers (ViTs) have demonstrated impressive performance in v...

Boosting Adversarial Transferability using Dynamic Cues

The transferability of adversarial perturbations between image models ha...

Boosting Cross-task Transferability of Adversarial Patches with Visual Relations

The transferability of adversarial examples is a crucial aspect of evalu...

Please sign up or login with your details

Forgot password? Click here to reset