{"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/backdoor-removal-for-generative-large","title":"Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models","arxiv_id":"2405.07667","date":"2024-05-13","proceeding":null,"authors":["Haoran Li","Yulin Chen","Zihao Zheng","Qi Hu","Chunkit Chan","Heshan Liu","Yangqiu Song"],"abstract":"With rapid advances, generative large language models (LLMs) dominate various Natural Language Processing (NLP) tasks from understanding to reasoning. Yet, language models' inherent vulnerabilities may be exacerbated due to increased accessibility and unrestricted model training on massive data. A malicious adversary may publish poisoned data online and conduct backdoor attacks on the victim LLMs pre-trained on the poisoned data. Backdoored LLMs behave innocuously for normal queries and generate harmful responses when the backdoor trigger is activated. Despite significant efforts paid to LLMs' safety issues, LLMs are still struggling against backdoor attacks. As Anthropic recently revealed, existing safety training strategies, including supervised fine-tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), fail to revoke the backdoors once the LLM is backdoored during the pre-training stage. In this paper, we present Simulate and Eliminate (SANDE) to erase the undesired backdoored mappings for generative LLMs. We initially propose Overwrite Supervised Fine-tuning (OSFT) for effective backdoor removal when the trigger is known. Then, to handle scenarios where trigger patterns are unknown, we integrate OSFT into our two-stage framework, SANDE. Unlike other works that assume access to cleanly trained models, our safety-enhanced LLMs are able to revoke backdoors without any reference. Consequently, our safety-enhanced LLMs no longer produce targeted responses when the backdoor triggers are activated. We conduct comprehensive experiments to show that our proposed SANDE is effective against backdoor attacks while bringing minimal harm to LLMs' powerful capability.","url_abs":"https://arxiv.org/abs/2405.07667v2","url_pdf":"https://arxiv.org/pdf/2405.07667v2.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":"backdoor-removal-for-generative-large","repo_url":"https://github.com/HKUST-KnowComp/SANDE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.07667","atlas_url":"https://app.syntology.ai/?focus=2405.07667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07667"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.07667"},"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":"2405.07667"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.07667\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2405.07667"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2405.07667\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2405.07667"},"call":"get_concepts_for_paper(arxiv_id=\"2405.07667\")"}],"by_repo":[{"repo":"HKUST-KnowComp/SANDE","kind":"official","samples":7,"ran":7,"instrument":0,"unverified":0}],"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/2405.07667.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/2405.07667.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/HKUST-KnowComp/SANDE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7},"n_samples":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"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":{"official":{"samples":7,"ran":7,"n_ran_checked":7,"n_instrument":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,"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","signature_not_shown":"the graph records a signature for this sample and it is not shown; signature_not_shown_because names why, as the export's field-exclusion reason","signature_not_shown_because":{"signature_is_harness_object_repr":"an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape"}},"n_ran_with_level_date":7,"n_ran_without_level_date":0,"n_ran_signature_not_shown":1,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","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":"f217ff4ee51b4a30","code_sha256_prefix":"f217ff4ee51b4a30","entry":"exist_and_not_none","repo":"HKUST-KnowComp/SANDE","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/HKUST-KnowComp/SANDE/blob/HEAD/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"d:dict/0/?, key:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f217ff4ee51b4a30"}},{"code_sha256":"f7c48c9631124114","code_sha256_prefix":"f7c48c9631124114","entry":"get_eval_ds_config","repo":"HKUST-KnowComp/SANDE","repo_kind":"official","path":"deepspeed_utils.py","file_url":"https://github.com/HKUST-KnowComp/SANDE/blob/HEAD/deepspeed_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"offload:bool/0/bool, stage:int/0/int, bf16:bool/0/bool","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-eval-ds-config","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f7c48c9631124114"}},{"code_sha256":"e075b810b6afd6d1","code_sha256_prefix":"e075b810b6afd6d1","entry":"get_optimizer_grouped_parameters","repo":"HKUST-KnowComp/SANDE","repo_kind":"official","path":"deepspeed_utils.py","file_url":"https://github.com/HKUST-KnowComp/SANDE/blob/HEAD/deepspeed_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, weight_decay:float/0/float, no_decay_name_list:list/1/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e075b810b6afd6d1"}},{"code_sha256":"53710fec31027c67","code_sha256_prefix":"53710fec31027c67","entry":"get_tokenizer","repo":"HKUST-KnowComp/SANDE","repo_kind":"official","path":"eval_utility.py","file_url":"https://github.com/HKUST-KnowComp/SANDE/blob/HEAD/eval_utility.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_object_repr","fixture_out_type":"Mock","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-tokenizer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"53710fec31027c67"}},{"code_sha256":"05904ae9639815b8","code_sha256_prefix":"05904ae9639815b8","entry":"get_train_ds_config","repo":"HKUST-KnowComp/SANDE","repo_kind":"official","path":"deepspeed_utils.py","file_url":"https://github.com/HKUST-KnowComp/SANDE/blob/HEAD/deepspeed_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"offload:bool/0/bool, adam_offload:bool/0/bool, stage:int/0/int, bf16:bool/0/bool, max_norm:float/0/float, zpg:int/0/int, grad_accum_dtype:NoneType/0/?, disable_trace_cache:bool/0/bool","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-train-ds-config","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"05904ae9639815b8"}},{"code_sha256":"775a2e3aee27b5c8","code_sha256_prefix":"775a2e3aee27b5c8","entry":"preprocess_data","repo":"HKUST-KnowComp/SANDE","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/HKUST-KnowComp/SANDE/blob/HEAD/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"data:dict/0/?, pretrain_mode:bool/0/bool, trigger_marker_pair:NoneType/0/?, is_train:bool/0/bool, backdoor_rate:float/0/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/preprocess-data","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"775a2e3aee27b5c8"}},{"code_sha256":"c48a5c183e44469e","code_sha256_prefix":"c48a5c183e44469e","entry":"zero_pad_sequences","repo":"HKUST-KnowComp/SANDE","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/HKUST-KnowComp/SANDE/blob/HEAD/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"sequences:list/1/Tensor, side:str/0/str, value:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c48a5c183e44469e"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5defab7ac06758f56781458b0eed3be6ae41c12cd41064235f5a2e365d371941","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}