{"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/rethinking-the-backdoor-attacks-triggers-a","title":"Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective","arxiv_id":"2104.03413","date":"2021-04-07","proceeding":"ICCV 2021 10","authors":["Yi Zeng","Won Park","Z. Morley Mao","Ruoxi Jia"],"abstract":"Backdoor attacks have been considered a severe security threat to deep learning. Such attacks can make models perform abnormally on inputs with predefined triggers and still retain state-of-the-art performance on clean data. While backdoor attacks have been thoroughly investigated in the image domain from both attackers' and defenders' sides, an analysis in the frequency domain has been missing thus far. This paper first revisits existing backdoor triggers from a frequency perspective and performs a comprehensive analysis. Our results show that many current backdoor attacks exhibit severe high-frequency artifacts, which persist across different datasets and resolutions. We further demonstrate these high-frequency artifacts enable a simple way to detect existing backdoor triggers at a detection rate of 98.50% without prior knowledge of the attack details and the target model. Acknowledging previous attacks' weaknesses, we propose a practical way to create smooth backdoor triggers without high-frequency artifacts and study their detectability. We show that existing defense works can benefit by incorporating these smooth triggers into their design consideration. Moreover, we show that the detector tuned over stronger smooth triggers can generalize well to unseen weak smooth triggers. In short, our work emphasizes the importance of considering frequency analysis when designing both backdoor attacks and defenses in deep learning.","url_abs":"https://arxiv.org/abs/2104.03413v4","url_pdf":"https://arxiv.org/pdf/2104.03413v4.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":"rethinking-the-backdoor-attacks-triggers-a","repo_url":"https://github.com/YiZeng623/frequency-backdoor","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2104.03413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03413"}},"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":"deterministic:regex_extraction","url":"https://github.com/YiZeng623/frequency-backdoor","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":"d4e7f2f02076d61c","entry":"gauss_smooth","repo":"YiZeng623/frequency-backdoor","repo_kind":"official","path":"Sec5_Smooth_Trigger/gauss_smooth.py","file_url":"https://github.com/YiZeng623/frequency-backdoor/blob/HEAD/Sec5_Smooth_Trigger/gauss_smooth.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":"d4e7f2f02076d61c"}},{"code_sha256_prefix":"dfb6883fc6ed9988","entry":"jacobian","repo":"YiZeng623/frequency-backdoor","repo_kind":"official","path":"Sec5_Smooth_Trigger/target_universal.py","file_url":"https://github.com/YiZeng623/frequency-backdoor/blob/HEAD/Sec5_Smooth_Trigger/target_universal.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":"dfb6883fc6ed9988"}},{"code_sha256_prefix":"df113a59813760b1","entry":"normalization","repo":"YiZeng623/frequency-backdoor","repo_kind":"official","path":"Sec5_Smooth_Trigger/gauss_smooth.py","file_url":"https://github.com/YiZeng623/frequency-backdoor/blob/HEAD/Sec5_Smooth_Trigger/gauss_smooth.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":"df113a59813760b1"}},{"code_sha256_prefix":"82da29c6298f012a","entry":"tar_deepfool","repo":"YiZeng623/frequency-backdoor","repo_kind":"official","path":"Sec5_Smooth_Trigger/deepfool.py","file_url":"https://github.com/YiZeng623/frequency-backdoor/blob/HEAD/Sec5_Smooth_Trigger/deepfool.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":"82da29c6298f012a"}},{"code_sha256_prefix":"632b7b52eee34480","entry":"tensor2img","repo":"YiZeng623/frequency-backdoor","repo_kind":"official","path":"Sec5_Smooth_Trigger/gauss_smooth.py","file_url":"https://github.com/YiZeng623/frequency-backdoor/blob/HEAD/Sec5_Smooth_Trigger/gauss_smooth.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":"632b7b52eee34480"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}