paper-with-me

Papers

Zero-Knowledge Proof Based Verifiable Inference of Models

2025-11-25 · Yunxiao Wang arxiv

Recent advances in artificial intelligence (AI), particularly deep learning, have led to widespread adoption across various applications. Yet, a fundamental challenge persists: how can we verify the correctness of AI model inference when model owners cannot (or will not) reveal their parameters? These parameters represent enormous training costs and valuable intellectual property, making transparent verification difficult. In this paper, we introduce a zero-knowledge framework capable of verifying deep learning inference without exposing model internal parameters. Built on recursively composed zero-knowledge proofs and requiring no trusted setup, our framework supports both linear and nonlinear neural network layers, including matrix multiplication, normalization, softmax, and SiLU. Leveraging the Fiat-Shamir heuristic, we obtain a succinct non-interactive argument of knowledge (zkSNARK) with constant-size proofs. To demonstrate the practicality of our approach, we translate the DeepSeek model into a fully SNARK-verifiable version named ZK-DeepSeek and show experimentally that our framework delivers both efficiency and flexibility in real-world AI verification workloads.

📄 PDF Abstract BibTeX arXiv:2511.19902

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

NANOZK: Layerwise Zero-Knowledge Proofs for Verifiable Large Language Model Inference

2026-03-17 · Zhaohui Geoffrey Wang arxiv

When users query proprietary LLM APIs, they receive outputs with no cryptographic assurance that the claimed model was actually used. Service providers could substitute cheaper models, apply aggressive quantization, or r…

A Survey of Zero-Knowledge Proof Based Verifiable Machine Learning

2025-02-25 · Zhizhi Peng, Taotao Wang, Chonghe Zhao, Guofu Liao 외

As machine learning technologies advance rapidly across various domains, concerns over data privacy and model security have grown significantly. These challenges are particularly pronounced when models are trained and de…

Privacy Preserving

DIAP: A Decentralized Agent Identity Protocol with Zero-Knowledge Proofs and a Hybrid P2P Stack

2025-11-06 · Yuanjie Liu, Wenpeng Xing, Ye Zhou, Gaowei Chang 외 arxiv

The absence of a fully decentralized, verifiable, and privacy-preserving communication protocol for autonomous agents remains a core challenge in decentralized computing. Existing systems often rely on centralized interm…

Zero-Knowledge Proofs in Sublinear Space

2025-08-30 · Logan Nye arxiv

Zero-knowledge proofs allow verification of computations without revealing private information. However, existing systems require memory proportional to the computation size, which has historically limited use in large-s…

DSperse: A Framework for Targeted Verification in Zero-Knowledge Machine Learning

2025-08-09 · Dan Ivanov, Tristan Freiberg, Shirin Shahabi, Jonathan Gold 외 arxiv

DSperse is a modular framework for distributed machine learning inference with strategic cryptographic verification. Operating within the emerging paradigm of distributed zero-knowledge machine learning, DSperse avoids t…