{"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/onion-a-simple-and-effective-defense-against","title":"ONION: A Simple and Effective Defense Against Textual Backdoor Attacks","arxiv_id":"2011.10369","date":"2020-11-20","proceeding":"EMNLP 2021 11","authors":["Fanchao Qi","Yangyi Chen","Mukai Li","Yuan YAO","Zhiyuan Liu","Maosong Sun"],"abstract":"Backdoor attacks are a kind of emergent training-time threat to deep neural networks (DNNs). They can manipulate the output of DNNs and possess high insidiousness. In the field of natural language processing, some attack methods have been proposed and achieve very high attack success rates on multiple popular models. Nevertheless, there are few studies on defending against textual backdoor attacks. In this paper, we propose a simple and effective textual backdoor defense named ONION, which is based on outlier word detection and, to the best of our knowledge, is the first method that can handle all the textual backdoor attack situations. Experiments demonstrate the effectiveness of our model in defending BiLSTM and BERT against five different backdoor attacks. All the code and data of this paper can be obtained at https://github.com/thunlp/ONION.","url_abs":"https://arxiv.org/abs/2011.10369v3","url_pdf":"https://arxiv.org/pdf/2011.10369v3.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":"onion-a-simple-and-effective-defense-against","repo_url":"https://github.com/thunlp/ONION","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"onion-a-simple-and-effective-defense-against","repo_url":"https://github.com/lancopku/rap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"backdoor-attack","task_name":"Backdoor Attack"},{"task_slug":"backdoor-defense","task_name":"backdoor defense"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.10369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.10369"}},"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/lancopku/rap","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thunlp/ONION","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"0a3034959f19105b","entry":"filter_sent","repo":"thunlp/ONION","repo_kind":"official","path":"experiments/test_defense.py","file_url":"https://github.com/thunlp/ONION/blob/HEAD/experiments/test_defense.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a3034959f19105b"}},{"code_sha256_prefix":"0762630368cd3261","entry":"get_all_data","repo":"thunlp/ONION","repo_kind":"official","path":"experiments/run_poison_bert.py","file_url":"https://github.com/thunlp/ONION/blob/HEAD/experiments/run_poison_bert.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0762630368cd3261"}},{"code_sha256_prefix":"213b3de0b016d2f7","entry":"read_data","repo":"thunlp/ONION","repo_kind":"official","path":"experiments/run_poison_bert.py","file_url":"https://github.com/thunlp/ONION/blob/HEAD/experiments/run_poison_bert.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"213b3de0b016d2f7"}},{"code_sha256_prefix":"31ff894ab3f7a745","entry":"evaluaion","repo":"thunlp/ONION","repo_kind":"official","path":"experiments/run_poison_bert.py","file_url":"https://github.com/thunlp/ONION/blob/HEAD/experiments/run_poison_bert.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":"31ff894ab3f7a745"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}