{"paper":{"title":"Subtle Injection for Ground-truth Inference of LLM Training Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Abraham Itzhak Weinberg","submitted_at":"2026-05-18T14:48:44Z","abstract_excerpt":"As large language models (LLMs) are increasingly trained on scraped web corpora without authorisation, content owners require forensic methods to prove that their documents were included in a model's training set. We propose \\textbf{SIGIL} (\\textbf{S}ubtle \\textbf{I}njection for \\textbf{G}round-truth \\textbf{I}nference of \\textbf{L}LM training data), a framework that embeds imperceptible \\emph{canary sequences} into protected text and code such that any LLM trained on those documents exhibits statistically detectable behavioural signatures when probed with targeted queries.\n  SIGIL defines fiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06502","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.06502/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}