Hard-Sample Style Guided Patch Attack With RL-Enhanced Motion Pattern for Video Recognition
- 25 December 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 1205-1215
Abstract
Adversarial attacks have been extensively studied in the image field. In recent years, research has shown that video recognition models are also vulnerable to adversarial examples. However, most studies about adversarial attacks for video models have focused on perturbation-based methods, while patch-based black-box attacks have received less attention. Despite the excellent performance of perturbationbased attacks, these attacks are impractical for real-world implementation. Most existing patch-based black-box attacks require occluding larger areas and performing more queries to the target model. In this paper, we propose a hardsample style guided patch attack with reinforcement learning (RL) enhanced motion patterns for video recognition (HSPA). Specifically, we utilize the style features of video hard samples and transfer their multi-dimensional style features to images to obtain a texture patch set. Then we use reinforcement learning to locate the patch coordinates and obtain a specific adversarial motion pattern of the patch to successfully perform an effective attack on a video recognition model in both the spatial and temporal dimensions. Our experiments on three widely-used video action recognition models (C3D, LRCN, and TDN) and two mainstream datasets (UCF-101 and HMDB-51) demonstrate the superior performance of our method compared to other state-of-the-art approaches.Keywords
Funding Information
- National Natural Science Foundation of China (62106158)
- Research and Development Program of Beijing Municipal Education Commission (KM202210028007)
- R&D Program of Beijing Municipal Education Commission (KZ20231002822)
This publication has 37 references indexed in Scilit:
- Sparse Black-Box Video Attack with Reinforcement LearningInternational Journal of Computer Vision, 2022
- Bias-Based Universal Adversarial Patch Attack for Automatic Check-Out2020
- PatchAttack: A Black-Box Texture-Based Attack with Reinforcement Learning2020
- Improving the Robustness of Deep Neural Networks via Stability Training2016
- Image Style Transfer Using Convolutional Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- Long-term recurrent convolutional networks for visual recognition and description2015
- Understanding deep image representations by inverting them2015
- UCF‐101, A Novel Omi/HtrA2 Inhibitor, Protects Against Cerebral Ischemia/Reperfusion Injury in RatsThe Anatomical Record, 2009
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992