{"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/postmark-a-robust-blackbox-watermark-for","title":"PostMark: A Robust Blackbox Watermark for Large Language Models","arxiv_id":"2406.14517","date":"2024-06-20","proceeding":null,"authors":["Yapei Chang","Kalpesh Krishna","Amir Houmansadr","John Wieting","Mohit Iyyer"],"abstract":"The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits, which LLM API providers are loath to share due to fears of model distillation. As such, these watermarks must be implemented independently by each LLM provider. In this paper, we develop PostMark, a modular post-hoc watermarking procedure in which an input-dependent set of words (determined via a semantic embedding) is inserted into the text after the decoding process has completed. Critically, PostMark does not require logit access, which means it can be implemented by a third party. We also show that PostMark is more robust to paraphrasing attacks than existing watermarking methods: our experiments cover eight baseline algorithms, five base LLMs, and three datasets. Finally, we evaluate the impact of PostMark on text quality using both automated and human assessments, highlighting the trade-off between quality and robustness to paraphrasing. We release our code, outputs, and annotations at https://github.com/lilakk/PostMark.","url_abs":"https://arxiv.org/abs/2406.14517v2","url_pdf":"https://arxiv.org/pdf/2406.14517v2.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":"postmark-a-robust-blackbox-watermark-for","repo_url":"https://github.com/lilakk/postmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.14517","atlas_url":"https://app.syntology.ai/?focus=2406.14517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14517"}},"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/lilakk/postmark","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/lilakk/PostMark","reach":{"status":"ok"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"c52efc764d0b2940","entry":"compute_score","repo":"lilakk/PostMark","repo_kind":"official","path":"parse_human_annots.py","file_url":"https://github.com/lilakk/PostMark/blob/HEAD/parse_human_annots.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":"c52efc764d0b2940"}},{"code_sha256_prefix":"5ec1a729c347b708","entry":"determine_identity","repo":"lilakk/PostMark","repo_kind":"official","path":"parse_human_annots.py","file_url":"https://github.com/lilakk/PostMark/blob/HEAD/parse_human_annots.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5ec1a729c347b708"}},{"code_sha256_prefix":"7425f85ff7bae4f2","entry":"create_generation_record","repo":"lilakk/PostMark","repo_kind":"official","path":"postmark/watermark.py","file_url":"https://github.com/lilakk/PostMark/blob/HEAD/postmark/watermark.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":"7425f85ff7bae4f2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}