{"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/februus-input-purification-defense-against","title":"Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems","arxiv_id":"1908.03369","date":"2019-08-09","proceeding":null,"authors":["Bao Gia Doan","Ehsan Abbasnejad","Damith C. Ranasinghe"],"abstract":"We propose Februus; a new idea to neutralize highly potent and insidious Trojan attacks on Deep Neural Network (DNN) systems at run-time. In Trojan attacks, an adversary activates a backdoor crafted in a deep neural network model using a secret trigger, a Trojan, applied to any input to alter the model's decision to a target prediction---a target determined by and only known to the attacker. Februus sanitizes the incoming input by surgically removing the potential trigger artifacts and restoring the input for the classification task. Februus enables effective Trojan mitigation by sanitizing inputs with no loss of performance for sanitized inputs, Trojaned or benign. Our extensive evaluations on multiple infected models based on four popular datasets across three contrasting vision applications and trigger types demonstrate the high efficacy of Februus. We dramatically reduced attack success rates from 100% to near 0% for all cases (achieving 0% on multiple cases) and evaluated the generalizability of Februus to defend against complex adaptive attacks; notably, we realized the first defense against the advanced partial Trojan attack. To the best of our knowledge, Februus is the first backdoor defense method for operation at run-time capable of sanitizing Trojaned inputs without requiring anomaly detection methods, model retraining or costly labeled data.","url_abs":"https://arxiv.org/abs/1908.03369v6","url_pdf":"https://arxiv.org/pdf/1908.03369v6.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"februus-input-purification-defense-against","repo_url":"https://github.com/AdelaideAuto-IDLab/Februus","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.03369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03369"}},"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/AdelaideAuto-IDLab/Februus","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"179bb06adb6f63fe","entry":"normalize_tensor_batch","repo":"AdelaideAuto-IDLab/Februus","repo_kind":"official","path":"scene/Februus.py","file_url":"https://github.com/AdelaideAuto-IDLab/Februus/blob/HEAD/scene/Februus.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"179bb06adb6f63fe"}},{"code_sha256_prefix":"2513a256b82881ff","entry":"poison_one","repo":"AdelaideAuto-IDLab/Februus","repo_kind":"official","path":"traffic_sign/Februus.py","file_url":"https://github.com/AdelaideAuto-IDLab/Februus/blob/HEAD/traffic_sign/Februus.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2513a256b82881ff"}},{"code_sha256_prefix":"1ed9bb9126b74824","entry":"unno","repo":"AdelaideAuto-IDLab/Februus","repo_kind":"official","path":"face/Februus.py","file_url":"https://github.com/AdelaideAuto-IDLab/Februus/blob/HEAD/face/Februus.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1ed9bb9126b74824"}},{"code_sha256_prefix":"edeeafdddb31fd57","entry":"unno_cuda","repo":"AdelaideAuto-IDLab/Februus","repo_kind":"official","path":"face/Februus.py","file_url":"https://github.com/AdelaideAuto-IDLab/Februus/blob/HEAD/face/Februus.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"edeeafdddb31fd57"}},{"code_sha256_prefix":"1bbb71888e20120c","entry":"unnormalize","repo":"AdelaideAuto-IDLab/Februus","repo_kind":"official","path":"scene/Februus.py","file_url":"https://github.com/AdelaideAuto-IDLab/Februus/blob/HEAD/scene/Februus.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1bbb71888e20120c"}},{"code_sha256_prefix":"0ca46d0a76ae9d02","entry":"poison_one","repo":"AdelaideAuto-IDLab/Februus","repo_kind":"official","path":"face/Februus.py","file_url":"https://github.com/AdelaideAuto-IDLab/Februus/blob/HEAD/face/Februus.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ca46d0a76ae9d02"}},{"code_sha256_prefix":"eb9f97d93ec0750e","entry":"poison_one","repo":"AdelaideAuto-IDLab/Februus","repo_kind":"official","path":"scene/Februus.py","file_url":"https://github.com/AdelaideAuto-IDLab/Februus/blob/HEAD/scene/Februus.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb9f97d93ec0750e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}