{"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/benchmarking-vision-language-model-unlearning","title":"Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset","arxiv_id":"2411.03554","date":"2024-11-05","proceeding":null,"authors":["Yingzi Ma","Jiongxiao Wang","Fei Wang","Siyuan Ma","Jiazhao Li","Xiujun Li","Furong Huang","Lichao Sun","Bo Li","Yejin Choi","Muhao Chen","Chaowei Xiao"],"abstract":"Machine unlearning has emerged as an effective strategy for forgetting specific information in the training data. However, with the increasing integration of visual data, privacy concerns in Vision Language Models (VLMs) remain underexplored. To address this, we introduce Facial Identity Unlearning Benchmark (FIUBench), a novel VLM unlearning benchmark designed to robustly evaluate the effectiveness of unlearning algorithms under the Right to be Forgotten setting. Specifically, we formulate the VLM unlearning task via constructing the Fictitious Facial Identity VQA dataset and apply a two-stage evaluation pipeline that is designed to precisely control the sources of information and their exposure levels. In terms of evaluation, since VLM supports various forms of ways to ask questions with the same semantic meaning, we also provide robust evaluation metrics including membership inference attacks and carefully designed adversarial privacy attacks to evaluate the performance of algorithms. Through the evaluation of four baseline VLM unlearning algorithms within FIUBench, we find that all methods remain limited in their unlearning performance, with significant trade-offs between model utility and forget quality. Furthermore, our findings also highlight the importance of privacy attacks for robust evaluations. We hope FIUBench will drive progress in developing more effective VLM unlearning algorithms.","url_abs":"https://arxiv.org/abs/2411.03554v2","url_pdf":"https://arxiv.org/pdf/2411.03554v2.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":"benchmarking-vision-language-model-unlearning","repo_url":"https://github.com/safolab-wisc/fiubench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-unlearning","task_name":"Machine Unlearning"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.03554","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03554"}},"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/safolab-wisc/fiubench","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"unverified":16},"by_repo_kind":{"official":{"samples":18,"ran":2,"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":18,"samples":[{"code_sha256_prefix":"c774723322f1f9c6","entry":"find_all_linear_names","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/finetune.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":"c774723322f1f9c6"}},{"code_sha256_prefix":"dcd422d66b0581d8","entry":"get_cast_dtype","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"utils.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/utils.py","link_basis":"harvester_set","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":"dcd422d66b0581d8"}},{"code_sha256_prefix":"8f0487109c2e2ff5","entry":"eval_exact_match","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"evaluate_util.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/evaluate_util.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":"8f0487109c2e2ff5"}},{"code_sha256_prefix":"ece33b2e8d2088a3","entry":"find_all_linear_names","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"forget.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/forget.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":"ece33b2e8d2088a3"}},{"code_sha256_prefix":"c098ac4a54131e6f","entry":"find_eval_log_directories","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"results_collect.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/results_collect.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":"c098ac4a54131e6f"}},{"code_sha256_prefix":"68e3681d9b0cfc5e","entry":"get_forget_quality","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"aggregate_eval_stat.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/aggregate_eval_stat.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":"68e3681d9b0cfc5e"}},{"code_sha256_prefix":"11c1750458a81017","entry":"get_grouped_params","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"forget.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/forget.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":"11c1750458a81017"}},{"code_sha256_prefix":"06448b0513272463","entry":"get_model_identifiers_from_yaml","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"utils.py","file_url":"https://github.com/safolab-wisc/fiubench/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":"06448b0513272463"}},{"code_sha256_prefix":"bd5dfd6fc2dda7f0","entry":"get_model_utility","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"aggregate_eval_stat.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/aggregate_eval_stat.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":"bd5dfd6fc2dda7f0"}},{"code_sha256_prefix":"00990046679b0633","entry":"get_optimizer","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"forget.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/forget.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":"00990046679b0633"}},{"code_sha256_prefix":"d447636bcc8edade","entry":"get_text_inputs","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"eval/eval_mme.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/eval/eval_mme.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":"d447636bcc8edade"}},{"code_sha256_prefix":"05febc93f9059af6","entry":"load_model","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"eval/eval_mme.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/eval/eval_mme.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":"05febc93f9059af6"}},{"code_sha256_prefix":"1090886208057542","entry":"main","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"aggregate_eval_stat.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/aggregate_eval_stat.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":"1090886208057542"}},{"code_sha256_prefix":"e2eb6b8e9205ffdb","entry":"mme_forward","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"eval/eval_mme.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/eval/eval_mme.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":"e2eb6b8e9205ffdb"}},{"code_sha256_prefix":"402bcc5a4590066e","entry":"pad_qformer_input_ids","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"data_module.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/data_module.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":"402bcc5a4590066e"}},{"code_sha256_prefix":"af6791e6ec72eca8","entry":"pad_sequence","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"data_module.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/data_module.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":"af6791e6ec72eca8"}},{"code_sha256_prefix":"df30b18c6796c513","entry":"parse_pred_ans","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"utils.py","file_url":"https://github.com/safolab-wisc/fiubench/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":"df30b18c6796c513"}},{"code_sha256_prefix":"7e8b60de17458100","entry":"preprocess_v1","repo":"safolab-wisc/fiubench","repo_kind":"official","path":"data_module.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/data_module.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":"7e8b60de17458100"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}