{"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/influence-based-attributions-can-be","title":"Influence-based Attributions can be Manipulated","arxiv_id":"2409.05208","date":"2024-09-08","proceeding":null,"authors":["Chhavi Yadav","Ruihan Wu","Kamalika Chaudhuri"],"abstract":"Influence Functions are a standard tool for attributing predictions to training data in a principled manner and are widely used in applications such as data valuation and fairness. In this work, we present realistic incentives to manipulate influence-based attributions and investigate whether these attributions can be \\textit{systematically} tampered by an adversary. We show that this is indeed possible for logistic regression models trained on ResNet feature embeddings and standard tabular fairness datasets and provide efficient attacks with backward-friendly implementations. Our work raises questions on the reliability of influence-based attributions in adversarial circumstances. Code is available at : \\url{https://github.com/infinite-pursuits/influence-based-attributions-can-be-manipulated}","url_abs":"https://arxiv.org/abs/2409.05208v4","url_pdf":"https://arxiv.org/pdf/2409.05208v4.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":"influence-based-attributions-can-be","repo_url":"https://github.com/infinite-pursuits/influence-based-attributions-can-be-manipulated","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-valuation","task_name":"Data Valuation"},{"task_slug":"fairness","task_name":"Fairness"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"logistic-regression","method_name":"Logistic Regression"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.05208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05208"}},"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/infinite-pursuits/influence-based-attributions-can-be-manipulated","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":1,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"f4c9f096d90e61e3","entry":"conjugate_gradient","repo":"infinite-pursuits/influence-based-attributions-can-be-manipulated","repo_kind":"official","path":"downstream_multiclass/pytorch_influence_functions/influence_functions/utils.py","file_url":"https://github.com/infinite-pursuits/influence-based-attributions-can-be-manipulated/blob/HEAD/downstream_multiclass/pytorch_influence_functions/influence_functions/utils.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f4c9f096d90e61e3"}},{"code_sha256_prefix":"8fdbed480eb3cb54","entry":"find_acc","repo":"infinite-pursuits/influence-based-attributions-can-be-manipulated","repo_kind":"official","path":"downstream_multiclass/baseline.py","file_url":"https://github.com/infinite-pursuits/influence-based-attributions-can-be-manipulated/blob/HEAD/downstream_multiclass/baseline.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":"8fdbed480eb3cb54"}},{"code_sha256_prefix":"194db402fdfd8a1d","entry":"make_functional","repo":"infinite-pursuits/influence-based-attributions-can-be-manipulated","repo_kind":"official","path":"downstream_multiclass/pytorch_influence_functions/influence_functions/utils.py","file_url":"https://github.com/infinite-pursuits/influence-based-attributions-can-be-manipulated/blob/HEAD/downstream_multiclass/pytorch_influence_functions/influence_functions/utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"194db402fdfd8a1d"}},{"code_sha256_prefix":"1521d8f9fa289d3f","entry":"tensor_to_tuple","repo":"infinite-pursuits/influence-based-attributions-can-be-manipulated","repo_kind":"official","path":"downstream_multiclass/pytorch_influence_functions/influence_functions/utils.py","file_url":"https://github.com/infinite-pursuits/influence-based-attributions-can-be-manipulated/blob/HEAD/downstream_multiclass/pytorch_influence_functions/influence_functions/utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1521d8f9fa289d3f"}},{"code_sha256_prefix":"4c7fbcfed8667b92","entry":"fetch_data","repo":"infinite-pursuits/influence-based-attributions-can-be-manipulated","repo_kind":"official","path":"fairness_manipulation/dataset.py","file_url":"https://github.com/infinite-pursuits/influence-based-attributions-can-be-manipulated/blob/HEAD/fairness_manipulation/dataset.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":"4c7fbcfed8667b92"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}