DeepXplore: Automated Whitebox Testing of Deep Learning Systems

By Kexin Pei, Yinzhi Cao, Junfeng Yang, Suman Sekhar Jana. 2017

1,541 citations recorded by the source corpus.

Deep learning (DL) systems are increasingly deployed in safety- and security-critical domains including 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 whitebox framework for systematically testing real-world DL systems. First, we introduce neuron coverage for systematically 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 including 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%.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Signal Processing, Software Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Percy Liang
  2. Mohit Bansal
  3. Sergey Levine
  4. Yoshua Bengio
  5. Bo Li
  6. Quoc V. Le
  7. Luke S. Zettlemoyer
  8. Jianfeng Gao

In Safety, Robustness & Interpretability

  1. Nicholas Carlini
  2. Bo Li
  3. Suman Sekhar Jana
  4. Florian Tramèr
  5. Matthias Hein
  6. Cho-Jui Hsieh
  7. Huan Zhang
  8. Nicolas Papernot

In Signal Processing

  1. Bo Li
  2. Nicholas Carlini
  3. Battista Biggio
  4. Fabio Roli
  5. Dawn Song
  6. Suman Sekhar Jana
  7. Florian Tramèr
  8. Ian J. Goodfellow

In Software Engineering

  1. Suman Sekhar Jana
  2. Yang Liu
  3. Kexin Pei
  4. Bo Li
  5. Ian J. Goodfellow
  6. Battista Biggio
  7. Fabio Roli
  8. Aditya V. Thakur

Citations in the corpus