{"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/input-aware-dynamic-backdoor-attack","title":"Input-Aware Dynamic Backdoor Attack","arxiv_id":"2010.08138","date":"2020-10-16","proceeding":"NeurIPS 2020 12","authors":["Anh Nguyen","Anh Tran"],"abstract":"In recent years, neural backdoor attack has been considered to be a potential security threat to deep learning systems. Such systems, while achieving the state-of-the-art performance on clean data, perform abnormally on inputs with predefined triggers. Current backdoor techniques, however, rely on uniform trigger patterns, which are easily detected and mitigated by current defense methods. In this work, we propose a novel backdoor attack technique in which the triggers vary from input to input. To achieve this goal, we implement an input-aware trigger generator driven by diversity loss. A novel cross-trigger test is applied to enforce trigger nonreusablity, making backdoor verification impossible. Experiments show that our method is efficient in various attack scenarios as well as multiple datasets. We further demonstrate that our backdoor can bypass the state of the art defense methods. An analysis with a famous neural network inspector again proves the stealthiness of the proposed attack. Our code is publicly available at https://github.com/VinAIResearch/input-aware-backdoor-attack-release.","url_abs":"https://arxiv.org/abs/2010.08138v1","url_pdf":"https://arxiv.org/pdf/2010.08138v1.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":"input-aware-dynamic-backdoor-attack","repo_url":"https://github.com/VinAIResearch/input-aware-backdoor-attack-release","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"backdoor-attack","task_name":"Backdoor Attack"},{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.08138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08138"}},"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/VinAIResearch/input-aware-backdoor-attack-release","reach":null}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"dc19768e6ac5b095","entry":"Denormalize","repo":"VinAIResearch/input-aware-backdoor-attack-release","repo_kind":"official","path":"networks/models.py","file_url":"https://github.com/VinAIResearch/input-aware-backdoor-attack-release/blob/HEAD/networks/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc19768e6ac5b095"}},{"code_sha256_prefix":"7156d5cd0cdb284b","entry":"Normalize","repo":"VinAIResearch/input-aware-backdoor-attack-release","repo_kind":"official","path":"networks/models.py","file_url":"https://github.com/VinAIResearch/input-aware-backdoor-attack-release/blob/HEAD/networks/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7156d5cd0cdb284b"}},{"code_sha256_prefix":"b83416059766853e","entry":"Generator","repo":"VinAIResearch/input-aware-backdoor-attack-release","repo_kind":"official","path":"networks/models.py","file_url":"https://github.com/VinAIResearch/input-aware-backdoor-attack-release/blob/HEAD/networks/models.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":"b83416059766853e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}