Source · Tier A · Peer-reviewed

VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs

G. Liao, T. Wang, S. Zhang, J. Zhang, L. Shi, D. Tao. 2026. NDSS Symposium 2026.

Original	https://www.ndss-symposium.org/ndss-paper/verilora-fine-tuning-large-language-models-with-verifiable-security-via-zero-knowledge-proofs/
DOI	10.14722/ndss.2026.242361
arXiv	2508.21393
Version	Published at the NDSS Symposium 2026; the paper page, read on 2026-10-07, gives the title, authors and affiliations and shows no DOI. Crossref registers the DOI recorded here, which resolved to the NDSS paper PDF on 2026-10-17. Preprint arXiv 2508.21393 (DOI 10.48550/arXiv.2508.21393), first posted 29 August 2025; arXiv v3 dated 2 December 2025. The abstract and HTML, read on 2026-09-25, use the title VeriLoRA and state that the paper was accepted for publication at NDSS 2026.
Accessed	2026-10-13
Note	Proves one LoRA fine-tuning iteration (forward pass, backward pass, parameter update) on a single-sample minibatch for LLaMA-3.2 3B and 11B, LLaMA-2 7B and 13B and OPT 6.7B and 13B on one NVIDIA A100 80 GB GPU. The full text read reports 121.93–249.38 s of proving, 156–554 s of commitment generation and 1.87–3.73 s of verification per step. Code linked from arXiv v3 at https://github.com/liaoguofu/VeriLoRA, which serves the same repository as https://github.com/liaoguofu/zkLoRA (MIT licence, README titled VeriLoRA, built on the zkLLM code base). HEAD was 7cc0977917f80571542c307ed6d4344518a0d801 on 2026-10-13; the paper pins no commit.

Cited by