{"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/defending-against-backdoor-attacks-by-layer","title":"Defending Against Backdoor Attacks by Layer-wise Feature Analysis","arxiv_id":"2302.12758","date":"2023-02-24","proceeding":null,"authors":["Najeeb Moharram Jebreel","Josep Domingo-Ferrer","Yiming Li"],"abstract":"Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models. Unfortunately, doing so facilitates a new training-time attack (i.e., backdoor attack) against DNNs. This attack aims to induce misclassification of input samples containing adversary-specified trigger patterns. In this paper, we first conduct a layer-wise feature analysis of poisoned and benign samples from the target class. We find out that the feature difference between benign and poisoned samples tends to be maximum at a critical layer, which is not always the one typically used in existing defenses, namely the layer before fully-connected layers. We also demonstrate how to locate this critical layer based on the behaviors of benign samples. We then propose a simple yet effective method to filter poisoned samples by analyzing the feature differences between suspicious and benign samples at the critical layer. We conduct extensive experiments on two benchmark datasets, which confirm the effectiveness of our defense.","url_abs":"https://arxiv.org/abs/2302.12758v1","url_pdf":"https://arxiv.org/pdf/2302.12758v1.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":"defending-against-backdoor-attacks-by-layer","repo_url":"https://github.com/najeebjebreel/dbalfa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"backdoor-attack","task_name":"Backdoor Attack"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.12758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12758"}},"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/najeebjebreel/dbalfa","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"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":0,"samples":[{"code_sha256_prefix":"6197a19b88fb1aed","entry":"double_conv","repo":"najeebjebreel/dbalfa","repo_kind":"official","path":"core/attacks/LIRA.py","file_url":"https://github.com/najeebjebreel/dbalfa/blob/HEAD/core/attacks/LIRA.py","link_basis":"harvester_set","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":"6197a19b88fb1aed"}},{"code_sha256_prefix":"aa8e4685d62e34d7","entry":"ResNet","repo":"najeebjebreel/dbalfa","repo_kind":"official","path":"my_models/resnet.py","file_url":"https://github.com/najeebjebreel/dbalfa/blob/HEAD/my_models/resnet.py","link_basis":"harvester_set","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":"aa8e4685d62e34d7"}},{"code_sha256_prefix":"c469ddae1a6c4775","entry":"get_features","repo":"najeebjebreel/dbalfa","repo_kind":"official","path":"utils.py","file_url":"https://github.com/najeebjebreel/dbalfa/blob/HEAD/utils.py","link_basis":"harvester_set","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":"c469ddae1a6c4775"}},{"code_sha256_prefix":"fc7187cc1bac10cc","entry":"get_inference_result","repo":"najeebjebreel/dbalfa","repo_kind":"official","path":"core/attacks/Blind.py","file_url":"https://github.com/najeebjebreel/dbalfa/blob/HEAD/core/attacks/Blind.py","link_basis":"harvester_set","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":"fc7187cc1bac10cc"}},{"code_sha256_prefix":"e3052317d27ff60f","entry":"get_secret_acc","repo":"najeebjebreel/dbalfa","repo_kind":"official","path":"core/attacks/ISSBA.py","file_url":"https://github.com/najeebjebreel/dbalfa/blob/HEAD/core/attacks/ISSBA.py","link_basis":"harvester_set","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":"e3052317d27ff60f"}},{"code_sha256_prefix":"cb72b7e1024c31b0","entry":"l2_regularizer","repo":"najeebjebreel/dbalfa","repo_kind":"official","path":"my_models/curves.py","file_url":"https://github.com/najeebjebreel/dbalfa/blob/HEAD/my_models/curves.py","link_basis":"harvester_set","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":"cb72b7e1024c31b0"}},{"code_sha256_prefix":"3c2902242add3c64","entry":"my_imread","repo":"najeebjebreel/dbalfa","repo_kind":"official","path":"core/attacks/LabelConsistent.py","file_url":"https://github.com/najeebjebreel/dbalfa/blob/HEAD/core/attacks/LabelConsistent.py","link_basis":"harvester_set","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":"3c2902242add3c64"}},{"code_sha256_prefix":"b1cfa48eb3407994","entry":"th","repo":"najeebjebreel/dbalfa","repo_kind":"official","path":"core/attacks/Blind.py","file_url":"https://github.com/najeebjebreel/dbalfa/blob/HEAD/core/attacks/Blind.py","link_basis":"harvester_set","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":"b1cfa48eb3407994"}},{"code_sha256_prefix":"3dd252e1513af683","entry":"thp","repo":"najeebjebreel/dbalfa","repo_kind":"official","path":"core/attacks/Blind.py","file_url":"https://github.com/najeebjebreel/dbalfa/blob/HEAD/core/attacks/Blind.py","link_basis":"harvester_set","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":"3dd252e1513af683"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}