{"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/reflection-backdoor-a-natural-backdoor-attack","title":"Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks","arxiv_id":"2007.02343","date":"2020-07-05","proceeding":"ECCV 2020 8","authors":["Yunfei Liu","Xingjun Ma","James Bailey","Feng Lu"],"abstract":"Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at training time. A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of the training data. At test time, the victim model behaves normally on clean test data, yet consistently predicts a specific (likely incorrect) target class whenever the backdoor pattern is present in a test example. While existing backdoor attacks are effective, they are not stealthy. The modifications made on training data or labels are often suspicious and can be easily detected by simple data filtering or human inspection. In this paper, we present a new type of backdoor attack inspired by an important natural phenomenon: reflection. Using mathematical modeling of physical reflection models, we propose reflection backdoor (Refool) to plant reflections as backdoor into a victim model. We demonstrate on 3 computer vision tasks and 5 datasets that, Refool can attack state-of-the-art DNNs with high success rate, and is resistant to state-of-the-art backdoor defenses.","url_abs":"https://arxiv.org/abs/2007.02343v2","url_pdf":"https://arxiv.org/pdf/2007.02343v2.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":"reflection-backdoor-a-natural-backdoor-attack","repo_url":"https://github.com/BililiCode/ARGD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"reflection-backdoor-a-natural-backdoor-attack","repo_url":"https://github.com/DreamtaleCore/Refool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"reflection-backdoor-a-natural-backdoor-attack","repo_url":"https://github.com/bboylyg/NAD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"backdoor-attack","task_name":"Backdoor Attack"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.02343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02343"}},"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/bboylyg/NAD","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BililiCode/ARGD","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DreamtaleCore/Refool","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"c13ff56b116b021f","entry":"extract_list_from_dict","repo":"DreamtaleCore/Refool","repo_kind":"listed","path":"strategy.py","file_url":"https://github.com/DreamtaleCore/Refool/blob/HEAD/strategy.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c13ff56b116b021f"}},{"code_sha256_prefix":"fcd6809bdbf068ea","entry":"get_reflection_name","repo":"DreamtaleCore/Refool","repo_kind":"listed","path":"strategy.py","file_url":"https://github.com/DreamtaleCore/Refool/blob/HEAD/strategy.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fcd6809bdbf068ea"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}