用密码学方法实现粒子对撞机低延迟推理，保障速度与可信性。
Knowledge is Overrated: A zero-knowledge machine learning and cryptographic hashing-based framework for verifiable, low latency inference at the LHC
- 基于零知识机器学习和哈希技术，实现大模型快速推理
- 达成纳秒级延迟，满足40MHz在线触发要求
- 自带异常检测，适合高能物理实时分析场景
大型强子对撞机（LHC）运行依赖低延迟事件选择（触发）算法。现代机器学习模型在离线分类中表现优异，可提升触发性能，进而改善下游物理分析。然而，现有大型模型的推理无法满足LHC每秒4000万次（40MHz）的在线延迟约束。本文提出 exttt{PHAZE}框架，利用加密技术如哈希与零知识机器学习（zkML），通过可验证的提前退出机制，从任意大规模基线模型中实现低延迟推理。该框架可达到纳秒级延迟，具备内置异常检测能力，在LHC触发场景中展现固有优势，并有望在未来支持动态低层触发。
原文摘要 · Abstract (English)
Low latency event-selection (trigger) algorithms are essential components of Large Hadron Collider (LHC) operation. Modern machine learning (ML) models have shown great offline performance as classifiers and could improve trigger performance, thereby improving downstream physics analyses. However, inference on such large models does not satisfy the $40\text{MHz}$ online latency constraint at the LHC. In this work, we propose \texttt{PHAZE}, a novel framework built on cryptographic techniques like hashing and zero-knowledge machine learning (zkML) to achieve low latency inference, via a certifiable, early-exit mechanism from an arbitrarily large baseline model. We lay the foundations for such a framework to achieve nanosecond-order latency and discuss its inherent advantages, such as built-in anomaly detection, within the scope of LHC triggers, as well as its potential to enable a dynamic low-level trigger in the future.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。