Knowledge is Overrated: A zero-knowledge machine learning and cryptographic hashing-based framework for verifiable, low latency inference at the LHC

TL;DR

This paper introduces PHAZE, a cryptographic framework utilizing zero-knowledge ML and hashing to enable verifiable, low-latency inference for LHC triggers, overcoming traditional latency constraints of large models.

Contribution

The paper presents PHAZE, a novel cryptographic framework that achieves nanosecond-order latency for large ML models in LHC trigger systems using zero-knowledge techniques.

Findings

PHAZE enables low-latency, verifiable inference suitable for LHC triggers.

The framework incorporates an early-exit mechanism for large models.

Built-in anomaly detection enhances reliability.

Abstract

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.