{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/videopure-diffusion-based-adversarial","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","arxiv_id":"2501.14999","date":"2025-01-25","proceeding":null,"authors":["Kaixun Jiang","Zhaoyu Chen","Jiyuan Fu","Lingyi Hong","Jinglun Li","Wenqiang Zhang"],"abstract":"Recent work indicates that video recognition models are vulnerable to adversarial examples, posing a serious security risk to downstream applications. However, current research has primarily focused on adversarial attacks, with limited work exploring defense mechanisms. Furthermore, due to the spatial-temporal complexity of videos, existing video defense methods face issues of high cost, overfitting, and limited defense performance. Recently, diffusion-based adversarial purification methods have achieved robust defense performance in the image domain. However, due to the additional temporal dimension in videos, directly applying these diffusion-based adversarial purification methods to the video domain suffers performance and efficiency degradation. To achieve an efficient and effective video adversarial defense method, we propose the first diffusion-based video purification framework to improve video recognition models' adversarial robustness: VideoPure. Given an adversarial example, we first employ temporal DDIM inversion to transform the input distribution into a temporally consistent and trajectory-defined distribution, covering adversarial noise while preserving more video structure. Then, during DDIM denoising, we leverage intermediate results at each denoising step and conduct guided spatial-temporal optimization, removing adversarial noise while maintaining temporal consistency. Finally, we input the list of optimized intermediate results into the video recognition model for multi-step voting to obtain the predicted class. We investigate the defense performance of our method against black-box, gray-box, and adaptive attacks on benchmark datasets and models. Compared with other adversarial purification methods, our method overall demonstrates better defense performance against different attacks. Our code is available at https://github.com/deep-kaixun/VideoPure.","url_abs":"https://arxiv.org/abs/2501.14999v1","url_pdf":"https://arxiv.org/pdf/2501.14999v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"videopure-diffusion-based-adversarial","repo_url":"https://github.com/deep-kaixun/videopure","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-defense","task_name":"Adversarial Defense"},{"task_slug":"adversarial-purification","task_name":"Adversarial Purification"},{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"video-recognition","task_name":"Video Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.14999","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}