SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure

TL;DR

SafeML introduces a statistical monitoring approach for ML classifiers that detects distributional shifts in data, addressing safety and security concerns in critical applications by analyzing operational data using various distance measures.

Contribution

This paper presents a novel active monitoring method combining multiple statistical distance measures to detect shifts in data distribution for safety and security in ML systems.

Findings

Effective detection of distributional shifts in datasets

Potential to improve safety and security monitoring in ML applications

Preliminary results support the approach's viability

Abstract

Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not satisfied with an exclusive testing approach of otherwise inaccessible black-box systems. Especially the interaction between safety and security is a central challenge, as security violations can lead to compromised safety. The contribution of this paper to addressing both safety and security within a single concept of protection applicable during the operation of ML systems is active monitoring of the behaviour and the operational context of the data-driven system based on distance measures of the Empirical Cumulative Distribution Function (ECDF). We investigate abstract datasets (XOR, Spiral, Circle) and current security-specific datasets for intrusion detection (CICIDS2017) of simulated network traffic, using distributional shift detection measures including the Kolmogorov-Smirnov, Kuiper, Anderson-Darling, Wasserstein and mixed Wasserstein-Anderson-Darling measures. Our preliminary findings indicate that the approach can provide a basis for detecting whether the application context of an ML component is valid in the safety-security. Our preliminary code and results are available at https://github.com/ISorokos/SafeML.