{"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/spartan-networks-self-feature-squeezing","title":"Spartan Networks: Self-Feature-Squeezing Neural Networks for increased robustness in adversarial settings","arxiv_id":"1812.06815","date":"2018-12-17","proceeding":null,"authors":["François Menet","Paul Berthier","José M. Fernandez","Michel Gagnon"],"abstract":"Deep learning models are vulnerable to adversarial examples which are input\nsamples modified in order to maximize the error on the system. We introduce\nSpartan Networks, resistant deep neural networks that do not require input\npreprocessing nor adversarial training. These networks have an adversarial\nlayer designed to discard some information of the network, thus forcing the\nsystem to focus on relevant input. This is done using a new activation function\nto discard data. The added layer trains the neural network to filter-out\nusually-irrelevant parts of its input. Our performance evaluation shows that\nSpartan Networks have a slightly lower precision but report a higher robustness\nunder attack when compared to unprotected models. Results of this study of\nAdversarial AI as a new attack vector are based on tests conducted on the MNIST\ndataset.","url_abs":"http://arxiv.org/abs/1812.06815v1","url_pdf":"http://arxiv.org/pdf/1812.06815v1.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":"spartan-networks-self-feature-squeezing","repo_url":"https://github.com/FMenet/Spartan-Networks","is_official":0,"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}