Affiliation:
1. Columbia University
2. Johns Hopkins University
Abstract
Deep learning (DL) systems are increasingly deployed in safety- and security-critical domains such as self-driving cars and malware detection, where the correctness and predictability of a system's behavior for corner case inputs are of great importance. Existing DL testing depends heavily on manually labeled data and therefore often fails to expose erroneous behaviors for rare inputs.
We design, implement, and evaluate DeepXplore, the first white-box framework for systematically testing real-world DL systems. First, we introduce neuron coverage for measuring the parts of a DL system exercised by test inputs. Next, we leverage multiple DL systems with similar functionality as cross-referencing oracles to avoid manual checking. Finally, we demonstrate how finding inputs for DL systems that both trigger many differential behaviors and achieve high neuron coverage can be represented as a joint optimization problem and solved efficiently using gradient-based search techniques.
DeepXplore efficiently finds thousands of incorrect corner case behaviors (e.g., self-driving cars crashing into guard rails and malware masquerading as benign software) in state-of-the-art DL models with thousands of neurons trained on five popular datasets such as ImageNet and Udacity self-driving challenge data. For all tested DL models, on average, DeepXplore generated one test input demonstrating incorrect behavior within one second while running only on a commodity laptop. We further show that the test inputs generated by DeepXplore can also be used to retrain the corresponding DL model to improve the model's accuracy by up to 3%.
Publisher
Association for Computing Machinery (ACM)
Cited by
65 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Abstraction and Refinement: Towards Scalable and Exact Verification of Neural Networks;ACM Transactions on Software Engineering and Methodology;2024-02-05
2. Test Optimization in DNN Testing: A Survey;ACM Transactions on Software Engineering and Methodology;2024-01-27
3. Mutation testing of unsupervised learning systems;Journal of Systems Architecture;2024-01
4. Causality-driven Testing of Autonomous Driving Systems;ACM Transactions on Software Engineering and Methodology;2023-12-05
5. Robust Test Selection for Deep Neural Networks;IEEE Transactions on Software Engineering;2023-12