arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.00182cs.CRcs.AI
收藏

EigenAI:确定性推理,可验证结果

EigenAI: Deterministic Inference, Verifiable Results

EigenAI

David Ribeiro Alves, Vishnu Patankar, Matheus Pereira, Jamie Stephens, Nima Vaziri, Sreeram Kannan

AI总结:

EigenAI 是一个基于 EigenLayer 构建的可验证 AI 平台,结合确定性推理引擎和加密经济安全协议,实现可审计、可重现的 AI 推理结果,支持主权代理在安全性和性能上取得突破。

摘要:

EigenAI 是一个基于 EigenLayer 重质押生态系统构建的可验证 AI 平台。总体而言,它结合了确定性大型语言模型(LLM)推理引擎和一种由加密经济安全的乐观重执行协议,使得每个推理结果都可以被公开审计、重现,必要时可以经济地执行。不信任的运营商在固定的 GPU 架构上运行推理,签名并加密请求和响应,并将加密日志发布到 EigenDA。在挑战窗口期间,任何观察者都可以通过 EigenVerify 请求重执行;结果随后在受信任的执行环境(TEE)中以确定性方式重新计算,使用阈值释放的解密密钥,允许对私有数据进行公开挑战。由于推理本身是位精确的,验证仅需字节等价性检查,单个诚实副本足以检测欺诈。我们展示了这种架构如何产生主权代理——预测市场法官、交易机器人和科学助手——它们在继承以太坊验证器基础的安全性的同时,享有最先进的性能。

英文摘要:

EigenAI is a verifiable AI platform built on top of the EigenLayer restaking ecosystem. At a high level, it combines a deterministic large-language model (LLM) inference engine with a cryptoeconomically secured optimistic re-execution protocol so that every inference result can be publicly audited, reproduced, and, if necessary, economically enforced. An untrusted operator runs inference on a fixed GPU architecture, signs and encrypts the request and response, and publishes the encrypted log to EigenDA. During a challenge window, any watcher may request re-execution through EigenVerify; the result is then deterministically recomputed inside a trusted execution environment (TEE) with a threshold-released decryption key, allowing a public challenge with private data. Because inference itself is bit-exact, verification reduces to a byte-equality check, and a single honest replica suffices to detect fraud. We show how this architecture yields sovereign agents -- prediction-market judges, trading bots, and scientific assistants -- that enjoy state-of-the-art performance while inheriting security from Ethereum's validator base.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑