{"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/robust-ai-generated-text-detection-by","title":"Robust AI-Generated Text Detection by Restricted Embeddings","arxiv_id":"2410.08113","date":"2024-10-10","proceeding":null,"authors":["Kristian Kuznetsov","Eduard Tulchinskii","Laida Kushnareva","German Magai","Serguei Barannikov","Sergey Nikolenko","Irina Piontkovskaya"],"abstract":"Growing amount and quality of AI-generated texts makes detecting such content more difficult. In most real-world scenarios, the domain (style and topic) of generated data and the generator model are not known in advance. In this work, we focus on the robustness of classifier-based detectors of AI-generated text, namely their ability to transfer to unseen generators or semantic domains. We investigate the geometry of the embedding space of Transformer-based text encoders and show that clearing out harmful linear subspaces helps to train a robust classifier, ignoring domain-specific spurious features. We investigate several subspace decomposition and feature selection strategies and achieve significant improvements over state of the art methods in cross-domain and cross-generator transfer. Our best approaches for head-wise and coordinate-based subspace removal increase the mean out-of-distribution (OOD) classification score by up to 9% and 14% in particular setups for RoBERTa and BERT embeddings respectively. We release our code and data: https://github.com/SilverSolver/RobustATD","url_abs":"https://arxiv.org/abs/2410.08113v1","url_pdf":"https://arxiv.org/pdf/2410.08113v1.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":"robust-ai-generated-text-detection-by","repo_url":"https://github.com/silversolver/robustatd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"text-detection","task_name":"Text Detection"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feature-selection","method_name":"Feature Selection"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.08113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08113"}},"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/silversolver/robustatd","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"893274839d9741ef","entry":"get_data","repo":"silversolver/robustatd","repo_kind":"official","path":"utils.py","file_url":"https://github.com/silversolver/robustatd/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":"893274839d9741ef"}},{"code_sha256_prefix":"d7413c0e227aa610","entry":"get_roberta_last_hidden_state","repo":"silversolver/robustatd","repo_kind":"official","path":"utils.py","file_url":"https://github.com/silversolver/robustatd/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":"d7413c0e227aa610"}},{"code_sha256_prefix":"925c0c91c92e7af1","entry":"loadFile","repo":"silversolver/robustatd","repo_kind":"official","path":"fit_eraser_probing_tasks.py","file_url":"https://github.com/silversolver/robustatd/blob/HEAD/fit_eraser_probing_tasks.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":"925c0c91c92e7af1"}},{"code_sha256_prefix":"e99730bed9668d68","entry":"get_embeddings","repo":"silversolver/robustatd","repo_kind":"official","path":"fit_eraser_probing_tasks.py","file_url":"https://github.com/silversolver/robustatd/blob/HEAD/fit_eraser_probing_tasks.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":"e99730bed9668d68"}},{"code_sha256_prefix":"6e90d22f1d7af677","entry":"tokenize","repo":"silversolver/robustatd","repo_kind":"official","path":"fit_eraser_probing_tasks.py","file_url":"https://github.com/silversolver/robustatd/blob/HEAD/fit_eraser_probing_tasks.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":"6e90d22f1d7af677"}},{"code_sha256_prefix":"325f76679a2a2e57","entry":"tokenized_semEval","repo":"silversolver/robustatd","repo_kind":"official","path":"utils.py","file_url":"https://github.com/silversolver/robustatd/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":"325f76679a2a2e57"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}