DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems

TL;DR

DeepGauge introduces multi-granularity testing criteria to evaluate and improve the robustness and generality of deep learning systems, addressing their vulnerabilities beyond mere accuracy metrics.

Contribution

It proposes a novel set of testing criteria for DL systems that provide a multi-faceted evaluation of their robustness and generality.

Findings

Effective in revealing vulnerabilities of DL systems

Applicable across multiple datasets and models

Enhances understanding of DL system robustness

Abstract

Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffer from various vulnerabilities which can lead to severe consequences when applied to real-world applications. Currently, the testing adequacy of a DL system is usually measured by the accuracy of test data. Considering the limitation of accessible high quality test data, good accuracy performance on test data can hardly provide confidence to the testing adequacy and generality of DL systems. Unlike traditional software systems that have clear and controllable logic and functionality, the lack of interpretability in a DL system makes system analysis and defect detection difficult, which could potentially hinder its real-world deployment. In this paper, we propose DeepGauge, a set of multi-granularity testing criteria for DL systems, which aims at rendering a multi-faceted portrayal of the testbed. The in-depth evaluation of our proposed testing criteria is demonstrated on two well-known datasets, five DL systems, and with four state-of-the-art adversarial attack techniques against DL. The potential usefulness of DeepGauge sheds light on the construction of more generic and robust DL systems.