# DLFuzz: Differential Fuzzing Testing of Deep Learning Systems

arXiv: https://arxiv.org/abs/1808.09413 · HTML: https://mlsanity.com/paper/1808.09413/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2018.

## Built on by (most cited first, 30 of 65)

- [Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench](https://mlsanity.com/paper/2308.03656/) (2023)
- [How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review](https://mlsanity.com/paper/2107.12045/) (2021)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Search](https://mlsanity.com/paper/2107.06997/) (2021)
- [Distribution-Aware Testing of Neural Networks Using Generative Models](https://mlsanity.com/paper/2102.13602/) (2021)
- [SoK: On the Semantic AI Security in Autonomous Driving](https://mlsanity.com/paper/2203.05314/) (2022)
- [When and Why Test Generators for Deep Learning Produce Invalid Inputs: an Empirical Study](https://mlsanity.com/paper/2212.11368/) (2022)
- [DeepMetis: Augmenting a Deep Learning Test Set to Increase its Mutation Score](https://mlsanity.com/paper/2109.07514/) (2021)
- [Exposing Previously Undetectable Faults in Deep Neural Networks](https://mlsanity.com/paper/2106.00576/) (2021)
- [Challenges and Practices of Deep Learning Model Reengineering: A Case Study on Computer Vision](https://mlsanity.com/paper/2303.07476/) (2023)
- [Comprehensive Evaluation of ChatGPT Reliability Through Multilingual Inquiries](https://mlsanity.com/paper/2312.10524/) (2023)
- [A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence](https://mlsanity.com/paper/2401.03188/) (2024)
- [Performance Analysis of Out-of-Distribution Detection on Various Trained Neural Networks](https://mlsanity.com/paper/2103.15580/) (2021)
- [Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimation](https://mlsanity.com/paper/2207.10942/) (2022)
- [Performance Analysis of Out-of-Distribution Detection on Trained Neural Networks](https://mlsanity.com/paper/2204.12378/) (2022)
- [A Tale of Two Models: Constructing Evasive Attacks on Edge Models](https://mlsanity.com/paper/2204.10933/) (2022)
- [FedDebug: Systematic Debugging for Federated Learning Applications](https://mlsanity.com/paper/2301.03553/) (2023)
- [Reusing Deep Neural Network Models through Model Re-engineering](https://mlsanity.com/paper/2304.00245/) (2023)
- [LEAP: Efficient and Automated Test Method for NLP Software](https://mlsanity.com/paper/2308.11284/) (2023)
- [CertPri: Certifiable Prioritization for Deep Neural Networks via Movement Cost in Feature Space](https://mlsanity.com/paper/2307.09375/) (2023)
- [Test & Evaluation Best Practices for Machine Learning-Enabled Systems](https://mlsanity.com/paper/2310.06800/) (2023)
- [Benchmarking Generative AI Models for Deep Learning Test Input Generation](https://mlsanity.com/paper/2412.17652/) (2024)
- [An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software](https://mlsanity.com/paper/2308.09810/) (2023)
- [DeepQTest: Testing Autonomous Driving Systems with Reinforcement Learning and Real-world Weather Data](https://mlsanity.com/paper/2310.05170/) (2023)
- [Targeted Deep Learning System Boundary Testing](https://mlsanity.com/paper/2408.06258/) (2024)
- [ML4ML: Automated Invariance Testing for Machine Learning Models](https://mlsanity.com/paper/2109.12926/) (2021)
- [Testing Feedforward Neural Networks Training Programs](https://mlsanity.com/paper/2204.00694/) (2022)
- [Characterizing and Understanding the Behavior of Quantized Models for Reliable Deployment](https://mlsanity.com/paper/2204.04220/) (2022)
- [A Tale of Two Approximations: Tightening Over-Approximation for DNN Robustness Verification via Under-Approximation](https://mlsanity.com/paper/2305.16998/) (2023)
- [QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems](https://mlsanity.com/paper/2402.12950/) (2024)

## Abstract (arXiv)

Deep learning (DL) systems are increasingly applied to safety-critical domains such as autonomous driving cars. It is of significant importance to ensure the reliability and robustness of DL systems. Existing testing methodologies always fail to include rare inputs in the testing dataset and exhibit low neuron coverage. In this paper, we propose DLFuzz, the frst differential fuzzing testing framework to guide DL systems exposing incorrect behaviors. DLFuzz keeps minutely mutating the input to maximize the neuron coverage and the prediction difference between the original input and the mutated input, without manual labeling effort or cross-referencing oracles from other DL systems with the same functionality. We present empirical evaluations on two well-known datasets to demonstrate its efficiency. Compared with DeepXplore, the state-of-the-art DL whitebox testing framework, DLFuzz does not require extra efforts to find similar functional DL systems for cross-referencing check, but could generate 338.59% more adversarial inputs with 89.82% smaller perturbations, averagely obtain 2.86% higher neuron coverage, and save 20.11% time consumption.