MLGuard: Defend Your Machine Learning Model!

TL;DR

MLGuard introduces a comprehensive framework for specifying, validating, and enforcing safety contracts in machine learning applications, addressing uncertainty and continual verification to enhance safety in critical domains.

Contribution

It presents a novel approach combining contract specification, probabilistic validation, and enforcement mechanisms for safer ML deployment.

Findings

Defines a new ML contract specification framework.

Generates validation models to assess contract violation probabilities.

Provides an enforcement mechanism to respond to violations.

Abstract

Machine Learning (ML) is used in critical highly regulated and high-stakes fields such as finance, medicine, and transportation. The correctness of these ML applications is important for human safety and economic benefit. Progress has been made on improving ML testing and monitoring of ML. However, these approaches do not provide i) pre/post conditions to handle uncertainty, ii) defining corrective actions based on probabilistic outcomes, or iii) continual verification during system operation. In this paper, we propose MLGuard, a new approach to specify contracts for ML applications. Our approach consists of a) an ML contract specification defining pre/post conditions, invariants, and altering behaviours, b) generated validation models to determine the probability of contract violation, and c) an ML wrapper generator to enforce the contract and respond to violations. Our work is intended to provide the overarching framework required for building ML applications and monitoring their safety.