{"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/backdoor-threats-from-compromised-foundation","title":"Backdoor Threats from Compromised Foundation Models to Federated Learning","arxiv_id":"2311.00144","date":"2023-10-31","proceeding":null,"authors":["Xi Li","Songhe Wang","Chen Wu","Hao Zhou","Jiaqi Wang"],"abstract":"Federated learning (FL) represents a novel paradigm to machine learning, addressing critical issues related to data privacy and security, yet suffering from data insufficiency and imbalance. The emergence of foundation models (FMs) provides a promising solution to the problems with FL. For instance, FMs could serve as teacher models or good starting points for FL. However, the integration of FM in FL presents a new challenge, exposing the FL systems to potential threats. This paper investigates the robustness of FL incorporating FMs by assessing their susceptibility to backdoor attacks. Contrary to classic backdoor attacks against FL, the proposed attack (1) does not require the attacker fully involved in the FL process; (2) poses a significant risk in practical FL scenarios; (3) is able to evade existing robust FL frameworks/ FL backdoor defenses; (4) underscores the researches on the robustness of FL systems integrated with FMs. The effectiveness of the proposed attack is demonstrated by extensive experiments with various well-known models and benchmark datasets encompassing both text and image classification domains.","url_abs":"https://arxiv.org/abs/2311.00144v1","url_pdf":"https://arxiv.org/pdf/2311.00144v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"backdoor-threats-from-compromised-foundation","repo_url":"https://github.com/lixi1994/backdoor_fm_fl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2311.00144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00144"}},"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/lixi1994/backdoor_fm_fl","reach":{"status":"ok"}}],"summary":{"ran":8,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":10,"samples":[{"code_sha256_prefix":"8fd68bd7ff5fe005","entry":"ResNet18","repo":"lixi1994/backdoor_fm_fl","repo_kind":"official","path":"resnet.py","file_url":"https://github.com/lixi1994/backdoor_fm_fl/blob/HEAD/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8fd68bd7ff5fe005"}},{"code_sha256_prefix":"0d1d4f95834b3ad1","entry":"ag_news_noniid","repo":"lixi1994/backdoor_fm_fl","repo_kind":"official","path":"sampling.py","file_url":"https://github.com/lixi1994/backdoor_fm_fl/blob/HEAD/sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0d1d4f95834b3ad1"}},{"code_sha256_prefix":"a247eb28b98075a9","entry":"global_model_KD","repo":"lixi1994/backdoor_fm_fl","repo_kind":"official","path":"update.py","file_url":"https://github.com/lixi1994/backdoor_fm_fl/blob/HEAD/update.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a247eb28b98075a9"}},{"code_sha256_prefix":"7a23bad1103f72ca","entry":"half_the_dataset","repo":"lixi1994/backdoor_fm_fl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lixi1994/backdoor_fm_fl/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7a23bad1103f72ca"}},{"code_sha256_prefix":"ea69c2edf80c7533","entry":"iid","repo":"lixi1994/backdoor_fm_fl","repo_kind":"official","path":"sampling.py","file_url":"https://github.com/lixi1994/backdoor_fm_fl/blob/HEAD/sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea69c2edf80c7533"}},{"code_sha256_prefix":"fc668bb1e5a4c2ac","entry":"pre_train_global_model","repo":"lixi1994/backdoor_fm_fl","repo_kind":"official","path":"update_image.py","file_url":"https://github.com/lixi1994/backdoor_fm_fl/blob/HEAD/update_image.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fc668bb1e5a4c2ac"}},{"code_sha256_prefix":"fa0156bd6102f857","entry":"sst2_noniid","repo":"lixi1994/backdoor_fm_fl","repo_kind":"official","path":"sampling.py","file_url":"https://github.com/lixi1994/backdoor_fm_fl/blob/HEAD/sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fa0156bd6102f857"}},{"code_sha256_prefix":"5e2c6e7a07121f39","entry":"test_inference","repo":"lixi1994/backdoor_fm_fl","repo_kind":"official","path":"update_image.py","file_url":"https://github.com/lixi1994/backdoor_fm_fl/blob/HEAD/update_image.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5e2c6e7a07121f39"}},{"code_sha256_prefix":"3c2171afd5bb45c6","entry":"get_tokenizer","repo":"lixi1994/backdoor_fm_fl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lixi1994/backdoor_fm_fl/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c2171afd5bb45c6"}},{"code_sha256_prefix":"9c6b24333a4021f6","entry":"tokenize_dataset","repo":"lixi1994/backdoor_fm_fl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lixi1994/backdoor_fm_fl/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9c6b24333a4021f6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}