Metraipolis › archive › dc_89d2cc38c635

Tokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism Against Private Data Leakage in LLMs — arXiv:2610.00309

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00309
License (as archived)
CC0-1.0
Archived
2026-10-06T12:08:31.438Z
SHA-256 of the archived text
c3022ec3e42d0e9945411bacb754339631e4d46ee37fbf6adf56ea529f49c179
Stable URL of this page
https://metraipolis.com/documento/dc_89d2cc38c635

How to cite

Tokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism Against Private Data Leakage in LLMs — arXiv:2610.00309 — arXiv (en), https://arxiv.org/abs/2610.00309 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89d2cc38c635 (Metraipolis archive dc_89d2cc38c635, sha256 c3022ec3e42d0e9945411bacb754339631e4d46ee37fbf6adf56ea529f49c179)
BibTeX
@misc{dc89d2cc38c635,
  title = {Tokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism Against Private Data Leakage in LLMs — arXiv:2610.00309},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00309},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89d2cc38c635; sha256 c3022ec3e42d0e9945411bacb754339631e4d46ee37fbf6adf56ea529f49c179},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00309. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly deployed in privacy-critical domains (e.g., healthcare, finance, and government), but their propensity to memorize and disclose personally identifiable information (PII) poses serious security and compliance risks. Existing defenses typically force a trade-off between model utility, privacy protection, and access to fine-tuned private knowledge. We propose LoRA-Oriented Control via Keyed Entry Tokens (Locket), a practical framework that embeds fine-grained, policy-driven access control directly into LLM generation. Locket trains a set of lightweight LoRA (Low-Rank Adaptation) adapters, each encoding a distinct access policy (e.g., full reveal, partial redaction via PII masking, or reveal under a specified differential privacy level). A compact gating module is trained to associate a learned keyed entry token with exactly one LoRA adapter via sequence-level hard routing; the presence of a valid token acts as an authorization key that unlocks corresponding private knowledge, while an invalid or absent token triggers a privacy-preserving adapter that redacts or sanitizes sensitive content. This design ensures Locket remains fully compatible with off-the-shelf LLMs, supporting scalable deployment while satisfying regulatory and privacy requirements. We evaluate Locket across multiple datasets (Enron, ECHR, Yelp) and a diverse set of state-of-the-art LLMs, including Qwen3 (1.7B and 8B), Meta's Llama-3.2 (1B and 3B), and Google's Gemma-2-2B. Our extensive experiments demonstrate that, when the correct token is provided, Locket preserves perplexity comparable to fine-tuning on raw data (without any defense). Conversely, when the token is missing or invalid, it substantially reduces PII leakage while maintaining utility and perplexity on par with strong baseline defenses.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.00309 — 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 2026-10-06T10:21:28.040Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).