{"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/smooth-adversarial-examples","title":"Smooth Adversarial Examples","arxiv_id":"1903.11862","date":"2019-03-28","proceeding":null,"authors":["Hanwei Zhang","Yannis Avrithis","Teddy Furon","Laurent Amsaleg"],"abstract":"This paper investigates the visual quality of the adversarial examples.\nRecent papers propose to smooth the perturbations to get rid of high frequency\nartefacts. In this work, smoothing has a different meaning as it perceptually\nshapes the perturbation according to the visual content of the image to be\nattacked. The perturbation becomes locally smooth on the flat areas of the\ninput image, but it may be noisy on its textured areas and sharp across its\nedges.\n  This operation relies on Laplacian smoothing, well-known in graph signal\nprocessing, which we integrate in the attack pipeline. We benchmark several\nattacks with and without smoothing under a white-box scenario and evaluate\ntheir transferability. Despite the additional constraint of smoothness, our\nattack has the same probability of success at lower distortion.","url_abs":"http://arxiv.org/abs/1903.11862v1","url_pdf":"http://arxiv.org/pdf/1903.11862v1.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":"smooth-adversarial-examples","repo_url":"https://github.com/hanwei0912/SmoothAdversarialExamples","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}