{"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/scaling-up-the-randomized-gradient-free","title":"Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks","arxiv_id":"1903.11359","date":"2019-03-27","proceeding":null,"authors":["Francesco Croce","Jonas Rauber","Matthias Hein"],"abstract":"Modern neural networks are highly non-robust against adversarial manipulation. A significant amount of work has been invested in techniques to compute lower bounds on robustness through formal guarantees and to build provably robust models. However, it is still difficult to get guarantees for larger networks or robustness against larger perturbations. Thus attack strategies are needed to provide tight upper bounds on the actual robustness. We significantly improve the randomized gradient-free attack for ReLU networks [9], in particular by scaling it up to large networks. We show that our attack achieves similar or significantly smaller robust accuracy than state-of-the-art attacks like PGD or the one of Carlini and Wagner, thus revealing an overestimation of the robustness by these state-of-the-art methods. Our attack is not based on a gradient descent scheme and in this sense gradient-free, which makes it less sensitive to the choice of hyperparameters as no careful selection of the stepsize is required.","url_abs":"https://arxiv.org/abs/1903.11359v2","url_pdf":"https://arxiv.org/pdf/1903.11359v2.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":"scaling-up-the-randomized-gradient-free","repo_url":"https://github.com/jonasrauber/linear-region-attack","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"}],"methods":[{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.11359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.11359"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jonasrauber/linear-region-attack","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"06085cbcf55df7ea","entry":"accuracy","repo":"jonasrauber/linear-region-attack","repo_kind":"official","path":"lr_attack.py","file_url":"https://github.com/jonasrauber/linear-region-attack/blob/HEAD/lr_attack.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"06085cbcf55df7ea"}},{"code_sha256_prefix":"fd8d31e9fcb41c96","entry":"l2_distance","repo":"jonasrauber/linear-region-attack","repo_kind":"official","path":"lr_attack.py","file_url":"https://github.com/jonasrauber/linear-region-attack/blob/HEAD/lr_attack.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fd8d31e9fcb41c96"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}