{"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/targeted-nonlinear-adversarial-perturbations","title":"Targeted Nonlinear Adversarial Perturbations in Images and Videos","arxiv_id":"1809.00958","date":"2018-08-27","proceeding":null,"authors":["Roberto Rey-de-Castro","Herschel Rabitz"],"abstract":"We introduce a method for learning adversarial perturbations targeted to\nindividual images or videos. The learned perturbations are found to be sparse\nwhile at the same time containing a high level of feature detail. Thus, the\nextracted perturbations allow a form of object or action recognition and\nprovide insights into what features the studied deep neural network models\nconsider important when reaching their classification decisions. From an\nadversarial point of view, the sparse perturbations successfully confused the\nmodels into misclassifying, although the perturbed samples still belonged to\nthe same original class by visual examination. This is discussed in terms of a\nprospective data augmentation scheme. The sparse yet high-quality perturbations\nmay also be leveraged for image or video compression.","url_abs":"http://arxiv.org/abs/1809.00958v1","url_pdf":"http://arxiv.org/pdf/1809.00958v1.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":"targeted-nonlinear-adversarial-perturbations","repo_url":"https://github.com/roberto1648/adversarial-perturbations-on-images-and-videos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"video-compression","task_name":"Video Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.00958","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}