{"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/nesterov-accelerated-gradient-and-scale","title":"Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks","arxiv_id":"1908.06281","date":"2019-08-17","proceeding":"ICLR 2020 1","authors":["Jiadong Lin","Chuanbiao Song","Kun He","Li-Wei Wang","John E. Hopcroft"],"abstract":"Deep learning models are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on benign inputs. However, under the black-box setting, most existing adversaries often have a poor transferability to attack other defense models. In this work, from the perspective of regarding the adversarial example generation as an optimization process, we propose two new methods to improve the transferability of adversarial examples, namely Nesterov Iterative Fast Gradient Sign Method (NI-FGSM) and Scale-Invariant attack Method (SIM). NI-FGSM aims to adapt Nesterov accelerated gradient into the iterative attacks so as to effectively look ahead and improve the transferability of adversarial examples. While SIM is based on our discovery on the scale-invariant property of deep learning models, for which we leverage to optimize the adversarial perturbations over the scale copies of the input images so as to avoid \"overfitting\" on the white-box model being attacked and generate more transferable adversarial examples. NI-FGSM and SIM can be naturally integrated to build a robust gradient-based attack to generate more transferable adversarial examples against the defense models. Empirical results on ImageNet dataset demonstrate that our attack methods exhibit higher transferability and achieve higher attack success rates than state-of-the-art gradient-based attacks.","url_abs":"https://arxiv.org/abs/1908.06281v5","url_pdf":"https://arxiv.org/pdf/1908.06281v5.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":"nesterov-accelerated-gradient-and-scale","repo_url":"https://github.com/JHL-HUST/SI-NI-FGSM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"nesterov-accelerated-gradient-and-scale","repo_url":"https://github.com/Trustworthy-AI-Group/TransferAttack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"nesterov-accelerated-gradient-and-scale","repo_url":"https://github.com/scenarri/s2m-tea","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"}],"methods":[{"method_slug":"nesterov-accelerated-gradient","method_name":"Nesterov Accelerated Gradient"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.06281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.06281"}},"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/Trustworthy-AI-Group/TransferAttack","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JHL-HUST/SI-NI-FGSM","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/scenarri/s2m-tea","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"db428026d8831b8e","entry":"load_labels","repo":"JHL-HUST/SI-NI-FGSM","repo_kind":"official","path":"simple_eval.py","file_url":"https://github.com/JHL-HUST/SI-NI-FGSM/blob/HEAD/simple_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"db428026d8831b8e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}