독서리서치레이더투자 프레임워크
로그인 / 회원가입
← 읽기로 돌아가기
뉴스주제 · FlashProve중대2 분 소요DisconfirmAI 편집부

Anthropic Releases FlashProve: Open-Source System Enables Verifiable LLM Inference

Anthropic launches FlashProve, using zkSNARK technology to let users quickly verify AI responses come from specific models without accessing weights.

2026-11-02 08:00 GMT+8

US-based AI company Anthropic released FlashProve on November 2, 2026, an open-source prototype system designed to solve the problem of "provable inference" for Large Language Models (LLMs). The system allows model providers to attach a short cryptographic proof to their responses, enabling users to verify within seconds that the reply was indeed generated by the claimed specific model, without needing access to the model's weights or specialized hardware.

This technology addresses trust challenges in the AI supply chain. Currently, users cannot determine if API results come from the premium model they paid for, or if they were secretly substituted by a routing service with a cheaper model, or even tampered with by attackers. FlashProve is built on Zero-Knowledge Succinct Arguments (zkSNARKs), a cryptographic tool that verifies computation integrity while hiding model weights with minimal computational overhead.

According to test data published by Anthropic, for a 400-billion-parameter mixture-of-experts model (Llama 4 Maverick, 4-bit quantized), a single H100 GPU generates proofs at approximately 110 tokens per second, with a proof size of about 19 MB per 1,024-token request. While this requires 70 to 95 times more GPU time than running the model directly using common libraries like vLLM, it represents a significant improvement over prior open-source systems, which were orders of magnitude slower.

Anthropic emphasizes that FlashProve is currently a prototype sharing intermediate progress, not a completed research agenda. Code, Lean formalization proofs, and technical reports are open-sourced under the Apache 2.0 license. This research not only helps enhance customer trust in AI providers but also offers potential tools for regulators to monitor AI development pacing and compliance, such as ensuring providers devote hardware to inference rather than secretly training new models.

로그인 / 회원가입
독서리서치레이더투자 프레임워크

출처

  • anthropic.com↗
주제

FlashProve

美国人工智能公司 Anthropic 于2026年11月2日发布了名为 FlashProve 的开源研究原型,旨在解决大语言模型推理过程中的“可验证性”难题。该系统利用 zkSNARK(零知识简洁论证)技术,允许用户在无法获取模型权重的情况…

2 단계1 건업데이트됨 2026-11-03 17:05

현재까지의 과정

  1. 2026-11-02Anthropic 发布 FlashProve 研究原型,介绍其基于 zkSNARK 的可验证推理机制及在 Llama 4 Maverick 上的初步性能数据。anthropic.com ↗
  2. 2026-11-03多家科技媒体(如 TokenPost, Blockchain.News)报道该发布,强调其每秒110令牌的证明生成速度及约70-95倍的GPU时间开销。tokenpost.com ↗

아직 해결되지 않은 문제

  • FlashProve 何时能优化到足以支持实时在线推理的低延迟水平?
  • 除了 Llama 4 Maverick,该系统在其他架构或更大规模模型上的表现如何?
  • 行业监管机构是否会采纳此类密码学证明作为合规审计的标准工具?
전체 주제 읽기 →
리서치 계속하기 →