{"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/hotflip-white-box-adversarial-examples-for","title":"HotFlip: White-Box Adversarial Examples for Text Classification","arxiv_id":"1712.06751","date":"2017-12-19","proceeding":"ACL 2018 7","authors":["Javid Ebrahimi","Anyi Rao","Daniel Lowd","Dejing Dou"],"abstract":"We propose an efficient method to generate white-box adversarial examples to\ntrick a character-level neural classifier. We find that only a few\nmanipulations are needed to greatly decrease the accuracy. Our method relies on\nan atomic flip operation, which swaps one token for another, based on the\ngradients of the one-hot input vectors. Due to efficiency of our method, we can\nperform adversarial training which makes the model more robust to attacks at\ntest time. With the use of a few semantics-preserving constraints, we\ndemonstrate that HotFlip can be adapted to attack a word-level classifier as\nwell.","url_abs":"http://arxiv.org/abs/1712.06751v2","url_pdf":"http://arxiv.org/pdf/1712.06751v2.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":"hotflip-white-box-adversarial-examples-for","repo_url":"https://github.com/AnyiRao/WordAdver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"hotflip-white-box-adversarial-examples-for","repo_url":"https://github.com/makcedward/nlpaug","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.06751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.06751"}},"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/makcedward/nlpaug","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AnyiRao/WordAdver","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"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":"64f43d9f5ab52d86","entry":"create_valid","repo":"AnyiRao/WordAdver","repo_kind":"listed","path":"lstm/sst2_lstm.py","file_url":"https://github.com/AnyiRao/WordAdver/blob/HEAD/lstm/sst2_lstm.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":"64f43d9f5ab52d86"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}