{"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/accumulative-poisoning-attacks-on-real-time","title":"Accumulative Poisoning Attacks on Real-time Data","arxiv_id":"2106.09993","date":"2021-06-18","proceeding":"NeurIPS 2021 12","authors":["Tianyu Pang","Xiao Yang","Yinpeng Dong","Hang Su","Jun Zhu"],"abstract":"Collecting training data from untrusted sources exposes machine learning services to poisoning adversaries, who maliciously manipulate training data to degrade the model accuracy. When trained on offline datasets, poisoning adversaries have to inject the poisoned data in advance before training, and the order of feeding these poisoned batches into the model is stochastic. In contrast, practical systems are more usually trained/fine-tuned on sequentially captured real-time data, in which case poisoning adversaries could dynamically poison each data batch according to the current model state. In this paper, we focus on the real-time settings and propose a new attacking strategy, which affiliates an accumulative phase with poisoning attacks to secretly (i.e., without affecting accuracy) magnify the destructive effect of a (poisoned) trigger batch. By mimicking online learning and federated learning on MNIST and CIFAR-10, we show that model accuracy significantly drops by a single update step on the trigger batch after the accumulative phase. Our work validates that a well-designed but straightforward attacking strategy can dramatically amplify the poisoning effects, with no need to explore complex techniques.","url_abs":"https://arxiv.org/abs/2106.09993v2","url_pdf":"https://arxiv.org/pdf/2106.09993v2.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":"accumulative-poisoning-attacks-on-real-time","repo_url":"https://github.com/ShawnXYang/AccumulativeAttack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.09993","atlas_url":"https://app.syntology.ai/?focus=2106.09993","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09993"}},"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/ShawnXYang/AccumulativeAttack","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"fa02a3a1df19980f","entry":"round_sign","repo":"ShawnXYang/AccumulativeAttack","repo_kind":"official","path":"online_accu_train.py","file_url":"https://github.com/ShawnXYang/AccumulativeAttack/blob/HEAD/online_accu_train.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fa02a3a1df19980f"}},{"code_sha256_prefix":"9ea4515ba91b15dd","entry":"gn_helper","repo":"ShawnXYang/AccumulativeAttack","repo_kind":"official","path":"feder_accu_train.py","file_url":"https://github.com/ShawnXYang/AccumulativeAttack/blob/HEAD/feder_accu_train.py","link_basis":"plan_row","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":"9ea4515ba91b15dd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}