{"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/ward-provable-rag-dataset-inference-via-llm","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","arxiv_id":"2410.03537","date":"2024-10-04","proceeding":null,"authors":["Nikola Jovanović","Robin Staab","Maximilian Baader","Martin Vechev"],"abstract":"RAG enables LLMs to easily incorporate external data, raising concerns for data owners regarding unauthorized usage of their content. The challenge of detecting such unauthorized usage remains underexplored, with datasets and methods from adjacent fields being ill-suited for its study. We take several steps to bridge this gap. First, we formalize this problem as (black-box) RAG Dataset Inference (RAG-DI). We then introduce a novel dataset designed for realistic benchmarking of RAG-DI methods, alongside a set of baselines. Finally, we propose Ward, a method for RAG-DI based on LLM watermarks that equips data owners with rigorous statistical guarantees regarding their dataset's misuse in RAG corpora. Ward consistently outperforms all baselines, achieving higher accuracy, superior query efficiency and robustness. Our work provides a foundation for future studies of RAG-DI and highlights LLM watermarks as a promising approach to this problem.","url_abs":"https://arxiv.org/abs/2410.03537v2","url_pdf":"https://arxiv.org/pdf/2410.03537v2.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":[],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"rag","task_name":"RAG"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"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":"rag","method_name":"RAG"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"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":{"syntology_url":"https://syntology.ai/paper/2410.03537","atlas_url":"https://app.syntology.ai/?focus=2410.03537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03537"}},"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":"deterministic:regex_extraction","url":"https://github.com/eth-sri/ward","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6},"by_repo_kind":{"found_in_text":{"samples":6,"ran":6,"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":0,"samples":[{"code_sha256_prefix":"3027055671300776","entry":"expand_dict_over_key","repo":"eth-sri/ward","repo_kind":"found_in_text","path":"src/config/meta_config.py","file_url":"https://github.com/eth-sri/ward/blob/HEAD/src/config/meta_config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3027055671300776"}},{"code_sha256_prefix":"30082b4c248c1b16","entry":"expand_dicts_over_key","repo":"eth-sri/ward","repo_kind":"found_in_text","path":"src/config/meta_config.py","file_url":"https://github.com/eth-sri/ward/blob/HEAD/src/config/meta_config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30082b4c248c1b16"}},{"code_sha256_prefix":"ed944c4bffb92311","entry":"get_bandicts","repo":"eth-sri/ward","repo_kind":"found_in_text","path":"src/rag_system.py","file_url":"https://github.com/eth-sri/ward/blob/HEAD/src/rag_system.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed944c4bffb92311"}},{"code_sha256_prefix":"0a14a852fc0dae57","entry":"index_dict","repo":"eth-sri/ward","repo_kind":"found_in_text","path":"src/config/meta_config.py","file_url":"https://github.com/eth-sri/ward/blob/HEAD/src/config/meta_config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a14a852fc0dae57"}},{"code_sha256_prefix":"ea86ca2f2c9bed9c","entry":"is_pattern","repo":"eth-sri/ward","repo_kind":"found_in_text","path":"src/rag_system.py","file_url":"https://github.com/eth-sri/ward/blob/HEAD/src/rag_system.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea86ca2f2c9bed9c"}},{"code_sha256_prefix":"c2299d0b8f737e84","entry":"load_data","repo":"eth-sri/ward","repo_kind":"found_in_text","path":"driver.py","file_url":"https://github.com/eth-sri/ward/blob/HEAD/driver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2299d0b8f737e84"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}