Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI

Heng Jin, Chaoyu Zhang, and Hexuan Yu, Virginia Tech; Shanghao Shi and Ning Zhang, Washington University in St. Louis; Y. Thomas Hou and Wenjing Lou, Virginia Tech

Cloud-based infrastructure has become the dominant platform for deploying large models, particularly large language models (LLMs). Fine-tuning and inference are increasingly delegated to cloud providers for simplified deployment and access to proprietary models, yet this creates a fundamental trust gap. Although cryptographic and TEE-based verification approaches exist, prohibitive proving costs and limited TEE memory prevent them from scaling to modern LLMs, leaving clients unable to practically audit these processes. This lack of transparency creates concrete security risks that can silently compromise service integrity.

We present AFTUNE, an auditable and verifiable framework that ensures the computational integrity of cloud-based fine-tuning and inference. AFTUNE incorporates a lightweight recording and spot-check mechanism that produces verifiable traces of execution. These traces enable clients to later audit whether the fine-tuning and inference processes followed the agreed configurations, by verifying sampled execution blocks inside a TEE, each covering only a small portion of the model and the execution trace. Our evaluation shows that AFTUNE adds modest overhead and makes auditing practical for clients.

USENIX Security '26 Open Access Sponsored by
King Abdullah University of Science and Technology (KAUST)

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {320889,
author = {Heng Jin and Chaoyu Zhang and Hexuan Yu and Shanghao Shi and Ning Zhang and Y. Thomas Hou and Wenjing Lou},
title = {Trusting What You Cannot See: Auditable {Fine-Tuning} and Inference for Proprietary {AI}},
booktitle = {35th USENIX Security Symposium (USENIX Security 26)},
year = {2026},
isbn = {978-1-939133-58-8},
address = {Baltimore, MD},
pages = {6067--6086},
url = {https://www.usenix.org/conference/usenixsecurity26/presentation/jin},
publisher = {USENIX Association},
month = aug
}