Metraipolis › archive › dc_2e6ff1c1cfdd
Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification — arXiv:2608.27954
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27954
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T10:48:01.718Z
- SHA-256 of the archived text
263497d488788f833fafd9be06ec904aa468a64e1bbcefbd8e998dc6a029080e- Stable URL of this page
https://metraipolis.com/documento/dc_2e6ff1c1cfdd
How to cite
Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification — arXiv:2608.27954 — arXiv (en), https://arxiv.org/abs/2608.27954 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e6ff1c1cfdd (Metraipolis archive dc_2e6ff1c1cfdd, sha256 263497d488788f833fafd9be06ec904aa468a64e1bbcefbd8e998dc6a029080e)
BibTeX
@misc{dc2e6ff1c1cfdd,
title = {Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification — arXiv:2608.27954},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27954},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e6ff1c1cfdd; sha256 263497d488788f833fafd9be06ec904aa468a64e1bbcefbd8e998dc6a029080e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27954. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Post-deployment changes to large language models can alter behavior while leaving routine outputs largely unchanged, creating a challenge for AI governance when model weights are proprietary. We present a privacy-preserving zk-SNARK-based audit framework that searches for probes designed in the spirit of adversarial examples to amplify logit drift between an approved model and a modified deployment. Our framework explores complementary probe families under different access models. Token-based probes operate in a black-box setting and require only the input interface, tokenizer, and vocabulary. Embedding-based probes require gray-box access to the embedding interface. Stress probes rely on additional interface capabilities but do not require full white-box access to model weights or architecture. This range allows probe selection to balance sensitivity, access requirements, and deployment cost. We evaluate probe constructions across LLM architectures, model-tampering scenarios representative of post-deployment attacks, and GPU platforms. Importantly, our experimental results demonstrate that token-based probes consistently deliver the strongest mean sensitivity across models and GPU platforms, although operating in a black-box setting. Our Groth16 zk-SNARK workflow remains practical as the probe set scales from 1 to 50, where proving time increases from 1.02 to 1.78 seconds, verification remains near 0.84 seconds, and proof size remains constant. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.27954 — 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 2026-10-17T10:33:42.484Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).