{"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/ho-fmn-hyperparameter-optimization-for-fast","title":"HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attacks","arxiv_id":"2407.08806","date":"2024-07-11","proceeding":null,"authors":["Raffaele Mura","Giuseppe Floris","Luca Scionis","Giorgio Piras","Maura Pintor","Ambra Demontis","Giorgio Giacinto","Battista Biggio","Fabio Roli"],"abstract":"Gradient-based attacks are a primary tool to evaluate robustness of machine-learning models. However, many attacks tend to provide overly-optimistic evaluations as they use fixed loss functions, optimizers, step-size schedulers, and default hyperparameters. In this work, we tackle these limitations by proposing a parametric variation of the well-known fast minimum-norm attack algorithm, whose loss, optimizer, step-size scheduler, and hyperparameters can be dynamically adjusted. We re-evaluate 12 robust models, showing that our attack finds smaller adversarial perturbations without requiring any additional tuning. This also enables reporting adversarial robustness as a function of the perturbation budget, providing a more complete evaluation than that offered by fixed-budget attacks, while remaining efficient. We release our open-source code at https://github.com/pralab/HO-FMN.","url_abs":"https://arxiv.org/abs/2407.08806v1","url_pdf":"https://arxiv.org/pdf/2407.08806v1.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":"ho-fmn-hyperparameter-optimization-for-fast","repo_url":"https://github.com/pralab/HO-FMN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"}],"methods":[{"method_slug":"fast-minimum-norm-attack","method_name":"Fast Minimum-Norm Attack"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}