Mechanism · Zero-knowledge proofs of training constraints
Sources
On this page
- AK. Abbaszadeh et al. (2024). Zero-Knowledge Proofs of Training for Deep Neural Networks. 2024 ACM SIGSAC Conference on Computer and Communications Security (CCS 2024), pp. 4316-4330. Source recordSupports: Kaizen zkPoT definition, techniques, threat model and costs · abstract; §1.2; evaluation
- AS. Waiwitlikhit et al. (2024). Trustless Audits without Revealing Data or Models. 41st International Conference on Machine Learning (ICML 2024). Source recordSupports: ZkAudit training proofs, costs, accuracy, limitations, code link · abstract; §3; §4–6; evaluation tables; §8
- AG. Liao et al. (2026). VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs. NDSS Symposium 2026. Source recordSupports: VeriLoRA zero-knowledge proofs of single LoRA fine-tuning steps for 3B–13B language models; hardware; costs; public code · abstract; evaluation
- BP. Peigné et al. (2026). Zero knowledge verification for frontier AI training is possible. arXiv. Source recordSupports: frontier-scale design, trust anchors, overhead estimates, open problems · abstract; §3.2; MOD. 1–4; Tables 1–2; App. A; App. G.5
- AZ. Peng et al. (2026). A Survey of Zero-Knowledge Proof Based Verifiable Machine Learning. Artificial Intelligence Review, vol. 59, no. 7, article 157. Source recordSupports: categorisation of verifiable training; survey-reported costs of other systems · §III-A1; Table IV
- AH. Sun et al. (2024). zkLLM: Zero Knowledge Proofs for Large Language Models. 2024 ACM SIGSAC Conference on Computer and Communications Security (CCS 2024). Source recordSupports: zkLLM authors' view of extending ZKPs to LLM training · §9