{"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/fall-of-empires-breaking-byzantine-tolerant","title":"Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation","arxiv_id":"1903.03936","date":"2019-03-10","proceeding":null,"authors":["Cong Xie","Sanmi Koyejo","Indranil Gupta"],"abstract":"Recently, new defense techniques have been developed to tolerate Byzantine\nfailures for distributed machine learning. The Byzantine model captures workers\nthat behave arbitrarily, including malicious and compromised workers. In this\npaper, we break two prevailing Byzantine-tolerant techniques. Specifically we\nshow robust aggregation methods for synchronous SGD -- coordinate-wise median\nand Krum -- can be broken using new attack strategies based on inner product\nmanipulation. We prove our results theoretically, as well as show empirical\nvalidation.","url_abs":"http://arxiv.org/abs/1903.03936v1","url_pdf":"http://arxiv.org/pdf/1903.03936v1.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":"fall-of-empires-breaking-byzantine-tolerant","repo_url":"https://github.com/bladesteam/blades","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fall-of-empires-breaking-byzantine-tolerant","repo_url":"https://github.com/lishenghui/blades","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fall-of-empires-breaking-byzantine-tolerant","repo_url":"https://github.com/sarthak-choudhary/hidra","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"fall-of-empires-breaking-byzantine-tolerant","repo_url":"https://github.com/wanglun1996/secure-robust-federated-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.03936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.03936"}},"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/lishenghui/blades","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wanglun1996/secure-robust-federated-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bladesteam/blades","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sarthak-choudhary/hidra","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"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":"cf2fc62d9c695c21","entry":"find_orthogonal_unit_vector","repo":"bladesteam/blades","repo_kind":"listed","path":"blades/adversaries/signguard_adversary.py","file_url":"https://github.com/bladesteam/blades/blob/HEAD/blades/adversaries/signguard_adversary.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf2fc62d9c695c21"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}