{"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/adversarial-perturbation-intensity-achieving","title":"Adversarial Perturbation Intensity Achieving Chosen Intra-Technique Transferability Level for Logistic Regression","arxiv_id":"1801.01953","date":"2018-01-06","proceeding":null,"authors":["Martin Gubri"],"abstract":"Machine Learning models have been shown to be vulnerable to adversarial\nexamples, ie. the manipulation of data by a attacker to defeat a defender's\nclassifier at test time. We present a novel probabilistic definition of\nadversarial examples in perfect or limited knowledge setting using prior\nprobability distributions on the defender's classifier. Using the asymptotic\nproperties of the logistic regression, we derive a closed-form expression of\nthe intensity of any adversarial perturbation, in order to achieve a given\nexpected misclassification rate. This technique is relevant in a threat model\nof known model specifications and unknown training data. To our knowledge, this\nis the first method that allows an attacker to directly choose the probability\nof attack success. We evaluate our approach on two real-world datasets.","url_abs":"http://arxiv.org/abs/1801.01953v1","url_pdf":"http://arxiv.org/pdf/1801.01953v1.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":"adversarial-perturbation-intensity-achieving","repo_url":"https://github.com/Framartin/adversarial-logistic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}