Zero-Knowledge ML

ML: Machine Learning

Follow this topic Ask about this topic

Latest papers

12 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

zkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language Models
Oct 6, 2026Junkai Liang, Zhanpeng Guo, Pengfei Wu +5Zero-Knowledge ML LLM Auditing
Peking University · Singapore Management University · China Telecom Quantum Information Technology Group Co., Ltd +1
Bits Under ZK-LLM: Evaluating Zero-Knowledge-Friendly Quantization for Verifiable Private LLM Inference
Sep 29, 2026Taeung Yoon, Yupeng Zhang, Xiaojing LiaoLLM Quantization LLM Inference
Siebel School of Computing and Data Science University of Illinois Urbana-Champaign
ServeGuard: Verifiable, Bounded-Residual Confinement of Operator-Invisible Channels Without Revealing the Certified Read Factor
Sep 18, 2026Dominik Dahlem, Rui VieiraZero-Knowledge ML LLM Security
Red Hat AI
Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification
Aug 28, 2026Cameron Wilding, Mina Shaker, Fatemeh GanjiLLM Auditing Zero-Knowledge ML
Worcester Polytechnic Institute Worcester, MA, USA
Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees
Aug 17, 2026Youwei Zhong, Ben Merbaum, Timos Antonopoulos +4Certified Robustness Neural Network Verification
Yale University · University of Illinois Urbana-Champaign
NiyamAI - An Intent-Bound AI Agent with Cryptographically Verifiable Guardrails using Zero-Knowledge Proofs
Aug 7, 2026Aditya Katkar, Om Karkele, Kartik Mandhane +2Tool-Augmented Language Model Agents LLM Guardrails
Department of Computer Engineering, Vishwakarma Institute of Technology, Pune, Maharashtra, India
ZK-SR117: A Chunked Zero-Knowledge Attestation Design for Aggregated Fair-Lending Metrics, with a Control Mapping toward Full SR 11-7 Coverage
Aug 1, 2026Mohammad Nasir Uddin, Rahnuma Tabassum Orpita, Eklachur Rahman Bhuiyan +1AI Risk Management Algorithmic Auditing
1DBA-BIDA (Business Intelligence and Data Analytics) Program, Westcliff University, USA · Department of Computer Science and Engineering, Northern University Bangladesh, Bangladesh · 3Washington University of Science and Technology, Alexandria, Virginia, USA +1
Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification
Jul 23, 2026Carter Luck, Olive Franzese-McLaughlin, Elisaweta Masserova +3Privacy-Preserving ML Black-Box Model Auditing
University of Massachusetts Amherst · Vector Institute · University of Toronto +3
Zero knowledge verification for frontier AI training is possible
Jun 3, 2026Pierre Peigné, Ky Nguyen, Paul WangZero-Knowledge ML AI Governance
Lefebvre General-Purpose AI Policy Lab Paris · Sorbonne Université, CNRS, LIP6 F-75005 Paris, France
NanoZK: Privacy-Preserving Verifiable Inference for Large Language Models via Layerwise Zero-Knowledge Proofs
Mar 17, 2026Zhaohui WangZero-Knowledge ML Privacy-Preserving ML
USC Viterbi School of Engineering, Los Angeles, CA, USA
Zero-Knowledge Federated Learning with Lattice-Based Hybrid Encryption for Quantum-Resilient Medical AI
Mar 3, 2026Edouard LansiauxQuantum Federated Learning Privacy-Preserving Federated Learning
Department of Emergency Medicine & STaR-AI Research Group, CHU de Lille, Université de Lille, Lille, France
Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge
Feb 19, 2026Wyatt Benno, Alberto Centelles, Antoine Douchet +1Zero-Knowledge ML Privacy-Preserving ML
ICME Labs

Oct 6, 2026J/K move · Enter open · S save

zkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language Models

Junkai Liang, Zhanpeng Guo, Pengfei Wu, Qingni Shen+4

Peking University · Singapore Management University · China Telecom Quantum Information Technology Group Co., Ltd+1

Zero-Knowledge ML LLM Auditing Privacy-Preserving ML Neural Network Verification Privacy-Preserving Language Models

Open paper AskPDF arXiv

Auditing the claimed outcomes of large language model (LLM) training is challenging when model weights and training data are private, while cryptographically proving the full training process is prohibitively expensive at Transformer scale. We present zkLLMPoT, a zero-knowledge framework that certifies auditor-defined properties of a trained checkpoint through forward evaluation rather than verification of its optimization trajectory. zkLLMPoT includes 2 phases: 1) The trainer fixes the architecture and the model weights are committed. Then the auditor selects challenge sequences, preventing the trainer from modifying the checkpoint in response to the audit data. 2) Then the trainer proves the objective value attained by the committed model on those sequences. This formulation makes the certification cost independent of the number of training iterations, without revealing model weights or requiring access to private training data. We build on sumcheck- and lookup-based arguments to certify Transformer computations, while supporting next-token loss and task-specific audit objectives. Across four model families, operator-level benchmarks yield proving times of 41-59 seconds for 1.1-1.5B-parameter models and 131 seconds at 13B for the covered operators, with verification below half a second at a sequence length of 512.