{"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/attack-of-the-tails-yes-you-really-can","title":"Attack of the Tails: Yes, You Really Can Backdoor Federated Learning","arxiv_id":"2007.05084","date":"2020-07-09","proceeding":"NeurIPS 2020 12","authors":["Hongyi Wang","Kartik Sreenivasan","Shashank Rajput","Harit Vishwakarma","Saurabh Agarwal","Jy-yong Sohn","Kangwook Lee","Dimitris Papailiopoulos"],"abstract":"Due to its decentralized nature, Federated Learning (FL) lends itself to adversarial attacks in the form of backdoors during training. The goal of a backdoor is to corrupt the performance of the trained model on specific sub-tasks (e.g., by classifying green cars as frogs). A range of FL backdoor attacks have been introduced in the literature, but also methods to defend against them, and it is currently an open question whether FL systems can be tailored to be robust against backdoors. In this work, we provide evidence to the contrary. We first establish that, in the general case, robustness to backdoors implies model robustness to adversarial examples, a major open problem in itself. Furthermore, detecting the presence of a backdoor in a FL model is unlikely assuming first order oracles or polynomial time. We couple our theoretical results with a new family of backdoor attacks, which we refer to as edge-case backdoors. An edge-case backdoor forces a model to misclassify on seemingly easy inputs that are however unlikely to be part of the training, or test data, i.e., they live on the tail of the input distribution. We explain how these edge-case backdoors can lead to unsavory failures and may have serious repercussions on fairness, and exhibit that with careful tuning at the side of the adversary, one can insert them across a range of machine learning tasks (e.g., image classification, OCR, text prediction, sentiment analysis).","url_abs":"https://arxiv.org/abs/2007.05084v1","url_pdf":"https://arxiv.org/pdf/2007.05084v1.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":"attack-of-the-tails-yes-you-really-can","repo_url":"https://github.com/ksreenivasan/OOD_Federated_Learning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"attack-of-the-tails-yes-you-really-can","repo_url":"https://github.com/pps-lab/fl-analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.05084","atlas_url":"https://app.syntology.ai/?focus=2007.05084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.05084"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ksreenivasan/OOD_Federated_Learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pps-lab/fl-analysis","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"ran_draft_wrong":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"396d2b49a5391613","entry":"bool_string","repo":"ksreenivasan/OOD_Federated_Learning","repo_kind":"official","path":"simulated_averaging.py","file_url":"https://github.com/ksreenivasan/OOD_Federated_Learning/blob/HEAD/simulated_averaging.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"396d2b49a5391613"}},{"code_sha256_prefix":"347d5ab57eebb4e5","entry":"create_ardis_test_dataset","repo":"ksreenivasan/OOD_Federated_Learning","repo_kind":"official","path":"generating_poisoned_DA.py","file_url":"https://github.com/ksreenivasan/OOD_Federated_Learning/blob/HEAD/generating_poisoned_DA.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"347d5ab57eebb4e5"}},{"code_sha256_prefix":"b5925300cc23dc11","entry":"getConfParamVal","repo":"ksreenivasan/OOD_Federated_Learning","repo_kind":"official","path":"language-tasks-fl/defense_runner.py","file_url":"https://github.com/ksreenivasan/OOD_Federated_Learning/blob/HEAD/language-tasks-fl/defense_runner.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5925300cc23dc11"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}