{"paper":{"title":"The Security Budget of Code LLMs: An Information-Theoretic Capacity-Security Bound","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Jianwei Tai","submitted_at":"2026-06-02T08:22:14Z","abstract_excerpt":"AI programming assistants make natural-language prompts a software-development interface, so small prompt perturbations become usability and security risks. We study an information-theoretic trade-off for code LLMs between functional capacity, $\\Cap=\\rmI(c^*;c_\\pi)$, and perturbation retention, $\\Sec=\\rmI(c_\\pi;\\tilde c_\\pi)$. Here $\\Sec$ is a retention-channel quantity, not a direct measure of exploit success or vulnerable-code generation. For code completion modeled as $p\\to c_\\pi$ with perturbed prompt $\\tilde p$, we prove $\\Cap+\\Sec\\le \\rmH(c^*)+\\rmI(p;\\tilde p)$, decomposing the budget in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03308","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/2606.03308/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"}