{"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/vectordefense-vectorization-as-a-defense-to","title":"VectorDefense: Vectorization as a Defense to Adversarial Examples","arxiv_id":"1804.08529","date":"2018-04-23","proceeding":null,"authors":["Vishaal Munusamy Kabilan","Brandon Morris","Anh Nguyen"],"abstract":"Training deep neural networks on images represented as grids of pixels has\nbrought to light an interesting phenomenon known as adversarial examples.\nInspired by how humans reconstruct abstract concepts, we attempt to codify the\ninput bitmap image into a set of compact, interpretable elements to avoid being\nfooled by the adversarial structures. We take the first step in this direction\nby experimenting with image vectorization as an input transformation step to\nmap the adversarial examples back into the natural manifold of MNIST\nhandwritten digits. We compare our method vs. state-of-the-art input\ntransformations and further discuss the trade-offs between a hand-designed and\na learned transformation defense.","url_abs":"http://arxiv.org/abs/1804.08529v1","url_pdf":"http://arxiv.org/pdf/1804.08529v1.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":"vectordefense-vectorization-as-a-defense-to","repo_url":"https://github.com/VishaalMK/VectorDefense","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"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}