{"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/shielded-representations-protecting-sensitive","title":"Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection","arxiv_id":"2305.10204","date":"2023-05-17","proceeding":null,"authors":["Shadi Iskander","Kira Radinsky","Yonatan Belinkov"],"abstract":"Natural language processing models tend to learn and encode social biases present in the data. One popular approach for addressing such biases is to eliminate encoded information from the model's representations. However, current methods are restricted to removing only linearly encoded information. In this work, we propose Iterative Gradient-Based Projection (IGBP), a novel method for removing non-linear encoded concepts from neural representations. Our method consists of iteratively training neural classifiers to predict a particular attribute we seek to eliminate, followed by a projection of the representation on a hypersurface, such that the classifiers become oblivious to the target attribute. We evaluate the effectiveness of our method on the task of removing gender and race information as sensitive attributes. Our results demonstrate that IGBP is effective in mitigating bias through intrinsic and extrinsic evaluations, with minimal impact on downstream task accuracy.","url_abs":"https://arxiv.org/abs/2305.10204v1","url_pdf":"https://arxiv.org/pdf/2305.10204v1.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":"shielded-representations-protecting-sensitive","repo_url":"https://github.com/technion-cs-nlp/igbp_nonlinear-removal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.10204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10204"}},"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/technion-cs-nlp/igbp_nonlinear-removal","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"5fd24afa6ef89a3c","entry":"build_probe","repo":"technion-cs-nlp/igbp_nonlinear-removal","repo_kind":"official","path":"src/debias_representation.py","file_url":"https://github.com/technion-cs-nlp/igbp_nonlinear-removal/blob/HEAD/src/debias_representation.py","link_basis":"first_harvest_node","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":"5fd24afa6ef89a3c"}},{"code_sha256_prefix":"321fdd140fa186a9","entry":"evaluate_probe","repo":"technion-cs-nlp/igbp_nonlinear-removal","repo_kind":"official","path":"src/debias_representation.py","file_url":"https://github.com/technion-cs-nlp/igbp_nonlinear-removal/blob/HEAD/src/debias_representation.py","link_basis":"first_harvest_node","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":"321fdd140fa186a9"}},{"code_sha256_prefix":"a0117f0eefa663ec","entry":"train_probe","repo":"technion-cs-nlp/igbp_nonlinear-removal","repo_kind":"official","path":"src/debias_representation.py","file_url":"https://github.com/technion-cs-nlp/igbp_nonlinear-removal/blob/HEAD/src/debias_representation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a0117f0eefa663ec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}