Metraipolis › archive › dc_25c9dbfcb708

Practical Secrets Extraction against Black-box LLMs — arXiv:2609.36941

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36941
License (as archived)
CC0-1.0
Archived
2026-10-07T17:26:54.546Z
SHA-256 of the archived text
0795e8ccc50507a3b5dc0ee9197e2a68b946097853988f25a5991c3082373a20
Stable URL of this page
https://metraipolis.com/documento/dc_25c9dbfcb708

How to cite

Practical Secrets Extraction against Black-box LLMs — arXiv:2609.36941 — arXiv (en), https://arxiv.org/abs/2609.36941 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_25c9dbfcb708 (Metraipolis archive dc_25c9dbfcb708, sha256 0795e8ccc50507a3b5dc0ee9197e2a68b946097853988f25a5991c3082373a20)
BibTeX
@misc{dc25c9dbfcb708,
  title = {Practical Secrets Extraction against Black-box LLMs — arXiv:2609.36941},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36941},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_25c9dbfcb708; sha256 0795e8ccc50507a3b5dc0ee9197e2a68b946097853988f25a5991c3082373a20},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36941. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) increasingly power autonomous coding agents such as Codex and Claude Code, yet their training corpora may contain confidential credentials exposed in public repositories or collected from private development artifacts, creating risks of memorization and subsequent leakage. Existing extraction audits, however, largely assume access to model weights or token probabilities. In this work, we present a black-box secret extraction framework for commercial, API-based LLMs under output-only access. It comprises (i) \emph{Cross-Validated Secret Knowledge Distillation}, which uses semantics-preserving prompt variants, response cross-validation, and provider-specific format filtering to distill secret-relevant behavior into a local white-box proxy; and (ii) \emph{Proxy-Guided Secret Extraction and Candidate Filtering}, which combines truncated top-$p$ sampling with local token entropy, $N$-gram frequency profiling, and provider-specific structural priors. On controlled API-key benchmarks, our framework improves recovery effectiveness and real-key rates over representative baselines while reducing extraction latency. A responsible real-world evaluation further recovers masked provider-specific credentials from three independently deployed black-box LLM systems spanning OpenAI and Claude Code, showing that memorized secrets can be exposed under output-only access.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.36941 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T16:58:17.344Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).