{"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/on-generation-of-adversarial-examples-using","title":"On Generation of Adversarial Examples using Convex Programming","arxiv_id":"1803.03607","date":"2018-03-09","proceeding":null,"authors":["Emilio Rafael Balda","Arash Behboodi","Rudolf Mathar"],"abstract":"It has been observed that deep learning architectures tend to make erroneous\ndecisions with high reliability for particularly designed adversarial\ninstances. In this work, we show that the perturbation analysis of these\narchitectures provides a framework for generating adversarial instances by\nconvex programming which, for classification tasks, is able to recover variants\nof existing non-adaptive adversarial methods. The proposed framework can be\nused for the design of adversarial noise under various desirable constraints\nand different types of networks. Moreover, this framework is capable of\nexplaining various existing adversarial methods and can be used to derive new\nalgorithms as well. We make use of these results to obtain novel algorithms.\nThe experiments show the competitive performance of the obtained solutions, in\nterms of fooling ratio, when benchmarked with well-known adversarial methods.","url_abs":"http://arxiv.org/abs/1803.03607v4","url_pdf":"http://arxiv.org/pdf/1803.03607v4.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":"on-generation-of-adversarial-examples-using","repo_url":"https://github.com/ebalda/adversarialconvex","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}