{"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/detecting-adversarial-examples-through","title":"Detecting Adversarial Examples through Nonlinear Dimensionality Reduction","arxiv_id":"1904.13094","date":"2019-04-30","proceeding":null,"authors":["Francesco Crecchi","Davide Bacciu","Battista Biggio"],"abstract":"Deep neural networks are vulnerable to adversarial examples, i.e.,\ncarefully-perturbed inputs aimed to mislead classification. This work proposes\na detection method based on combining non-linear dimensionality reduction and\ndensity estimation techniques. Our empirical findings show that the proposed\napproach is able to effectively detect adversarial examples crafted by\nnon-adaptive attackers, i.e., not specifically tuned to bypass the detection\nmethod. Given our promising results, we plan to extend our analysis to adaptive\nattackers in future work.","url_abs":"http://arxiv.org/abs/1904.13094v2","url_pdf":"http://arxiv.org/pdf/1904.13094v2.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":"detecting-adversarial-examples-through","repo_url":"https://github.com/FrancescoCrecchi/AE_Detector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.13094","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}