{"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/watermax-breaking-the-llm-watermark","title":"WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off","arxiv_id":"2403.04808","date":"2024-03-06","proceeding":null,"authors":["Eva Giboulot","Teddy Furon"],"abstract":"Watermarking is a technical means to dissuade malfeasant usage of Large Language Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that enjoys high detectability while sustaining the quality of the generated text of the original LLM. Its new design leaves the LLM untouched (no modification of the weights, logits, temperature, or sampling technique). WaterMax balances robustness and complexity contrary to the watermarking techniques of the literature inherently provoking a trade-off between quality and robustness. Its performance is both theoretically proven and experimentally validated. It outperforms all the SotA techniques under the most complete benchmark suite. Code available at https://github.com/eva-giboulot/WaterMax.","url_abs":"https://arxiv.org/abs/2403.04808v3","url_pdf":"https://arxiv.org/pdf/2403.04808v3.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":"watermax-breaking-the-llm-watermark","repo_url":"https://github.com/eva-giboulot/watermax","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.04808","atlas_url":"https://app.syntology.ai/?focus=2403.04808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04808"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eva-giboulot/watermax","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":"2006c2f6f6daa764","entry":"generate_mmw_path","repo":"eva-giboulot/watermax","repo_kind":"official","path":"test_sentence_wm.py","file_url":"https://github.com/eva-giboulot/watermax/blob/HEAD/test_sentence_wm.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":"2006c2f6f6daa764"}},{"code_sha256_prefix":"aa5abf5d87851c1c","entry":"get_detector","repo":"eva-giboulot/watermax","repo_kind":"official","path":"test_sentence_wm.py","file_url":"https://github.com/eva-giboulot/watermax/blob/HEAD/test_sentence_wm.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":"aa5abf5d87851c1c"}},{"code_sha256_prefix":"f59da376d411ca93","entry":"get_generator","repo":"eva-giboulot/watermax","repo_kind":"official","path":"test_sentence_wm.py","file_url":"https://github.com/eva-giboulot/watermax/blob/HEAD/test_sentence_wm.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":"f59da376d411ca93"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}