Themis: Automatic and Efficient Deep Learning System Testing with Strong Fault Detection Capability

TL;DR

Themis is an automatic testing system for deep learning systems that systematically detects faults with high coverage, significantly outperforming existing methods in fault detection and improving DLS accuracy after retraining.

Contribution

Themis introduces an automatic, systematic approach for deep learning system testing that achieves comprehensive fault coverage without manual effort, enhancing fault detection and model accuracy.

Findings

Themis detects 3.78 times more faults than existing techniques.

Retraining with faults found by Themis improves DLS accuracy by 14.7 times.

Themis effectively reveals fault-inducing data flows in various DLSs.

Abstract

Deep Learning Systems (DLSs) have been widely applied in safety-critical tasks such as autopilot. However, when a perturbed input is fed into a DLS for inference, the DLS often has incorrect outputs (i.e., faults). DLS testing techniques (e.g., DeepXplore) detect such faults by generating perturbed inputs to explore data flows that induce faults. Since a DLS often has infinitely many data flows, existing techniques require developers to manually specify a set of activation values in a DLS's neurons for exploring fault-inducing data flows. Unfortunately, recent studies show that such manual effort is tedious and can detect only a tiny proportion of fault-inducing data flows. In this paper, we present Themis, the first automatic DLS testing system, which attains strong fault detection capability by ensuring a full coverage of fault-inducing data flows at a high probability. Themis carries a new workflow for automatically and systematically revealing data flows whose internal neurons' outputs vary substantially when the inputs are slightly perturbed, as these data flows are likely fault-inducing. We evaluated Themis on ten different DLSs and found that on average the number of faults detected by Themis was 3.78X more than four notable DLS testing techniques. By retraining all evaluated DLSs with the detected faults, Themis also increased (regained) these DLSs' accuracies on average 14.7X higher than all baselines.