{"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/admix-enhancing-the-transferability-of","title":"Admix: Enhancing the Transferability of Adversarial Attacks","arxiv_id":"2102.00436","date":"2021-01-31","proceeding":"ICCV 2021 10","authors":["Xiaosen Wang","Xuanran He","Jingdong Wang","Kun He"],"abstract":"Deep neural networks are known to be extremely vulnerable to adversarial examples under white-box setting. Moreover, the malicious adversaries crafted on the surrogate (source) model often exhibit black-box transferability on other models with the same learning task but having different architectures. Recently, various methods are proposed to boost the adversarial transferability, among which the input transformation is one of the most effective approaches. We investigate in this direction and observe that existing transformations are all applied on a single image, which might limit the adversarial transferability. To this end, we propose a new input transformation based attack method called Admix that considers the input image and a set of images randomly sampled from other categories. Instead of directly calculating the gradient on the original input, Admix calculates the gradient on the input image admixed with a small portion of each add-in image while using the original label of the input to craft more transferable adversaries. Empirical evaluations on standard ImageNet dataset demonstrate that Admix could achieve significantly better transferability than existing input transformation methods under both single model setting and ensemble-model setting. By incorporating with existing input transformations, our method could further improve the transferability and outperforms the state-of-the-art combination of input transformations by a clear margin when attacking nine advanced defense models under ensemble-model setting. Code is available at https://github.com/JHL-HUST/Admix.","url_abs":"https://arxiv.org/abs/2102.00436v3","url_pdf":"https://arxiv.org/pdf/2102.00436v3.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":"admix-enhancing-the-transferability-of","repo_url":"https://github.com/JHL-HUST/Admix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"admix-enhancing-the-transferability-of","repo_url":"https://github.com/Trustworthy-AI-Group/TransferAttack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.00436","atlas_url":"https://app.syntology.ai/?focus=2102.00436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.00436"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/JHL-HUST/Admix","reach":{"status":"unanswered"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"918139489f26b489","entry":"Admix","repo":"Trustworthy-AI-Group/TransferAttack","repo_kind":"listed","path":"transferattack/input_transformation/admix.py","file_url":"https://github.com/Trustworthy-AI-Group/TransferAttack/blob/HEAD/transferattack/input_transformation/admix.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"918139489f26b489"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}