DeepAI AI Chat
Log In Sign Up

Model-based Exploration of the Frontier of Behaviours for Deep Learning System Testing

by   Vincenzo Riccio, et al.
USI Università della Svizzera italiana

With the increasing adoption of Deep Learning (DL) for critical tasks, such as autonomous driving, the evaluation of the quality of systems that rely on DL has become crucial. Once trained, DL systems produce an output for any arbitrary numeric vector provided as input, regardless of whether it is within or outside the validity domain of the system under test. Hence, the quality of such systems is determined by the intersection between their validity domain and the regions where their outputs exhibit a misbehaviour. In this paper, we introduce the notion of frontier of behaviours, i.e., the inputs at which the DL system starts to misbehave. If the frontier of misbehaviours is outside the validity domain of the system, the quality check is passed. Otherwise, the inputs at the intersection represent quality deficiencies of the system. We developed DeepJanus, a search-based tool that generates frontier inputs for DL systems. The experimental results obtained for the lane keeping component of a self-driving car show that the frontier of a well trained system contains almost exclusively unrealistic roads that violate the best practices of civil engineering, while the frontier of a poorly trained one includes many valid inputs that point to serious deficiencies of the system.


page 2

page 4

page 10


When and Why Test Generators for Deep Learning Produce Invalid Inputs: an Empirical Study

Testing Deep Learning (DL) based systems inherently requires large and r...

Data Sanity Check for Deep Learning Systems via Learnt Assertions

Deep learning (DL) techniques have demonstrated satisfactory performance...

DLFuzz: Differential Fuzzing Testing of Deep Learning Systems

Deep learning (DL) systems are increasingly applied to safety-critical d...

Guiding Deep Learning System Testing using Surprise Adequacy

Deep Learning (DL) systems are rapidly being adopted in safety and secur...

Graph-Based Fuzz Testing for Deep Learning Inference Engine

Testing deep learning (DL) systems are increasingly crucial as the incre...

DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Search

Deep Learning (DL) has been successfully applied to a wide range of appl...

Representing Deep Neural Networks Latent Space Geometries with Graphs

Deep Learning (DL) has attracted a lot of attention for its ability to r...