{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/badnets-identifying-vulnerabilities-in-the","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","arxiv_id":"1708.06733","date":"2017-08-22","proceeding":null,"authors":["Tianyu Gu","Brendan Dolan-Gavitt","Siddharth Garg"],"abstract":"Deep learning-based techniques have achieved state-of-the-art performance on\na wide variety of recognition and classification tasks. However, these networks\nare typically computationally expensive to train, requiring weeks of\ncomputation on many GPUs; as a result, many users outsource the training\nprocedure to the cloud or rely on pre-trained models that are then fine-tuned\nfor a specific task. In this paper we show that outsourced training introduces\nnew security risks: an adversary can create a maliciously trained network (a\nbackdoored neural network, or a \\emph{BadNet}) that has state-of-the-art\nperformance on the user's training and validation samples, but behaves badly on\nspecific attacker-chosen inputs. We first explore the properties of BadNets in\na toy example, by creating a backdoored handwritten digit classifier. Next, we\ndemonstrate backdoors in a more realistic scenario by creating a U.S. street\nsign classifier that identifies stop signs as speed limits when a special\nsticker is added to the stop sign; we then show in addition that the backdoor\nin our US street sign detector can persist even if the network is later\nretrained for another task and cause a drop in accuracy of {25}\\% on average\nwhen the backdoor trigger is present. These results demonstrate that backdoors\nin neural networks are both powerful and---because the behavior of neural\nnetworks is difficult to explicate---stealthy. This work provides motivation\nfor further research into techniques for verifying and inspecting neural\nnetworks, just as we have developed tools for verifying and debugging software.","url_abs":"http://arxiv.org/abs/1708.06733v2","url_pdf":"http://arxiv.org/pdf/1708.06733v2.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":"badnets-identifying-vulnerabilities-in-the","repo_url":"https://github.com/DreamtaleCore/Refool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"badnets-identifying-vulnerabilities-in-the","repo_url":"https://github.com/GeorgeTzannetos/badnets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"badnets-identifying-vulnerabilities-in-the","repo_url":"https://github.com/aisafety-hkust/backdoor_safety_tuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"badnets-identifying-vulnerabilities-in-the","repo_url":"https://github.com/aisafety-hkust/stable_backdoor_purification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"badnets-identifying-vulnerabilities-in-the","repo_url":"https://github.com/kooscii/badnets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"badnets-identifying-vulnerabilities-in-the","repo_url":"https://github.com/locuslab/breaking-poisoned-classifier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"badnets-identifying-vulnerabilities-in-the","repo_url":"https://github.com/sakshiudeshi/Neo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"badnets-identifying-vulnerabilities-in-the","repo_url":"https://github.com/trx14/TrojanNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"badnets-identifying-vulnerabilities-in-the","repo_url":"https://github.com/xandery-geek/BackdoorAttacks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"badnets-identifying-vulnerabilities-in-the","repo_url":"https://github.com/xqx12/daily-info","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"badnets-identifying-vulnerabilities-in-the","repo_url":"https://github.com/ain-soph/trojanzoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.06733","atlas_url":"https://app.syntology.ai/?focus=1708.06733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.06733"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1708.06733"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1708.06733"},"call":"get_harvested_code_for_paper(arxiv_id=\"1708.06733\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1708.06733"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1708.06733\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1708.06733"},"call":"get_concepts_for_paper(arxiv_id=\"1708.06733\")"}],"by_repo":[{"repo":"DreamtaleCore/Refool","kind":"listed","samples":2,"ran":2,"instrument":2,"unverified":0,"placed_by_identical_code":2},{"repo":"GeorgeTzannetos/badnets","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"aisafety-hkust/backdoor_safety_tuning","kind":"listed","samples":3,"ran":1,"instrument":0,"unverified":2},{"repo":"aisafety-hkust/stable_backdoor_purification","kind":"listed","samples":1,"ran":1,"instrument":1,"unverified":0,"placed_by_identical_code":1},{"repo":"kooscii/badnets","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"locuslab/breaking-poisoned-classifier","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2010.09080"],"harvested_for_calls":[{"arxiv_id":"2010.09080","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.09080"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.09080\")"}]},{"repo":"sakshiudeshi/Neo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"trx14/TrojanNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2006.08131"],"harvested_for_calls":[{"arxiv_id":"2006.08131","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.08131"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.08131\")"}]},{"repo":"xandery-geek/BackdoorAttacks","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2112.01148"],"harvested_for_calls":[{"arxiv_id":"2112.01148","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2112.01148"},"call":"get_harvested_code_for_paper(arxiv_id=\"2112.01148\")"}]},{"repo":"xqx12/daily-info","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ain-soph/trojanzoo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/1708.06733.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/1708.06733.svg"},"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/trx14/TrojanNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/GeorgeTzannetos/badnets","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ain-soph/trojanzoo","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/locuslab/breaking-poisoned-classifier","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aisafety-hkust/stable_backdoor_purification","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aisafety-hkust/backdoor_safety_tuning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DreamtaleCore/Refool","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xqx12/daily-info","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kooscii/badnets","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sakshiudeshi/Neo","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xandery-geek/BackdoorAttacks","reach":null}],"summary":{"ran_draft_wrong":3,"ran_violates":1,"ran_honours":2,"unverified":2},"n_samples":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":8,"ran":6,"n_ran_checked":3,"n_instrument":3,"repositories":4}},"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":8,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":1,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-22","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"efd3b8b851a0f5e7","code_sha256_prefix":"efd3b8b851a0f5e7","entry":"add_common_attack_args","repo":null,"repo_kind":"listed","path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"parser:SimpleArgumentParser/0/?","fixture_out_type":"SimpleArgumentParser","code_page":"/code/add-common-attack-args","census":null,"placed_by_identical_code":{"repo":"aisafety-hkust/stable_backdoor_purification","path":"attack/badnet.py","file_url":"https://github.com/AISafety-HKUST/stable_backdoor_purification/blob/HEAD/attack/badnet.py","papers":["2310.01875"],"is":"identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own"},"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"efd3b8b851a0f5e7"}},{"code_sha256":"5c6b89d763f0a8f3","code_sha256_prefix":"5c6b89d763f0a8f3","entry":"distillation","repo":"aisafety-hkust/backdoor_safety_tuning","repo_kind":"listed","path":"fine_tune/qra.py","file_url":"https://github.com/aisafety-hkust/backdoor_safety_tuning/blob/HEAD/fine_tune/qra.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"y:Tensor/2/float, labels:Tensor/1/int, teacher_scores:Tensor/2/float, temp:int/0/int, alpha:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/distillation","census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, aisafety-hkust/backdoor_safety_tuning (NOASSERTION)","mcp_get_code":{"code_sha256":"5c6b89d763f0a8f3"}},{"code_sha256":"4f825732b3b5e87e","code_sha256_prefix":"4f825732b3b5e87e","entry":"eval","repo":"GeorgeTzannetos/badnets","repo_kind":"listed","path":"train_eval.py","file_url":"https://github.com/GeorgeTzannetos/badnets/blob/HEAD/train_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"model:callable/0/?, test_loader:list/1/tuple, batch_size:int/0/int, report:bool/0/bool","fixture_out_type":"float","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/eval","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, GeorgeTzannetos/badnets when it was checked","mcp_get_code":{"code_sha256":"4f825732b3b5e87e"}},{"code_sha256":"c13ff56b116b021f","code_sha256_prefix":"c13ff56b116b021f","entry":"extract_list_from_dict","repo":null,"repo_kind":"listed","path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"i_dict:dict/0/?","fixture_out_type":"list","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"placed_by_identical_code":{"repo":"DreamtaleCore/Refool","path":"strategy.py","file_url":"https://github.com/DreamtaleCore/Refool/blob/HEAD/strategy.py","papers":["2007.02343"],"is":"identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own"},"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"c13ff56b116b021f"}},{"code_sha256":"fcd6809bdbf068ea","code_sha256_prefix":"fcd6809bdbf068ea","entry":"get_reflection_name","repo":null,"repo_kind":"listed","path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"s_pwd:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"fcd6809bdbf068ea"},"code_page":null,"census":null,"placed_by_identical_code":{"repo":"DreamtaleCore/Refool","path":"strategy.py","file_url":"https://github.com/DreamtaleCore/Refool/blob/HEAD/strategy.py","papers":["2007.02343"],"is":"identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own"},"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"fcd6809bdbf068ea"}},{"code_sha256":"53377da1ddefc4dd","code_sha256_prefix":"53377da1ddefc4dd","entry":"train","repo":"GeorgeTzannetos/badnets","repo_kind":"listed","path":"train_eval.py","file_url":"https://github.com/GeorgeTzannetos/badnets/blob/HEAD/train_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"model:callable/0/?, data_loader:list/1/tuple, criterion:callable/0/?, optimizer:SGD/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/train","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, GeorgeTzannetos/badnets when it was checked","mcp_get_code":{"code_sha256":"53377da1ddefc4dd"}},{"code_sha256":"bf4a97ed98a7136f","code_sha256_prefix":"bf4a97ed98a7136f","entry":"add_args","repo":"aisafety-hkust/backdoor_safety_tuning","repo_kind":"listed","path":"fine_tune/ft.py","file_url":"https://github.com/aisafety-hkust/backdoor_safety_tuning/blob/HEAD/fine_tune/ft.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/add-args","census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, aisafety-hkust/backdoor_safety_tuning (NOASSERTION)","mcp_get_code":{"code_sha256":"bf4a97ed98a7136f"}},{"code_sha256":"c8871bb5d53700cc","code_sha256_prefix":"c8871bb5d53700cc","entry":"add_args","repo":"aisafety-hkust/backdoor_safety_tuning","repo_kind":"listed","path":"fine_tune/qra.py","file_url":"https://github.com/aisafety-hkust/backdoor_safety_tuning/blob/HEAD/fine_tune/qra.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/add-args","census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, aisafety-hkust/backdoor_safety_tuning (NOASSERTION)","mcp_get_code":{"code_sha256":"c8871bb5d53700cc"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"df62758aad76e655e700294dd7114b843a9479de219bac8d5f7f03a4dc040216","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}