{"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/robustness-of-generalized-learning-vector","title":"Robustness of Generalized Learning Vector Quantization Models against Adversarial Attacks","arxiv_id":"1902.00577","date":"2019-02-01","proceeding":null,"authors":["Sascha Saralajew","Lars Holdijk","Maike Rees","Thomas Villmann"],"abstract":"Adversarial attacks and the development of (deep) neural networks robust\nagainst them are currently two widely researched topics. The robustness of\nLearning Vector Quantization (LVQ) models against adversarial attacks has\nhowever not yet been studied to the same extent. We therefore present an\nextensive evaluation of three LVQ models: Generalized LVQ, Generalized Matrix\nLVQ and Generalized Tangent LVQ. The evaluation suggests that both Generalized\nLVQ and Generalized Tangent LVQ have a high base robustness, on par with the\ncurrent state-of-the-art in robust neural network methods. In contrast to this,\nGeneralized Matrix LVQ shows a high susceptibility to adversarial attacks,\nscoring consistently behind all other models. Additionally, our numerical\nevaluation indicates that increasing the number of prototypes per class\nimproves the robustness of the models.","url_abs":"http://arxiv.org/abs/1902.00577v2","url_pdf":"http://arxiv.org/pdf/1902.00577v2.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":"robustness-of-generalized-learning-vector","repo_url":"https://github.com/LarsHoldijk/robust_LVQ_models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}