Write a Blog >>
ICSE 2023
Sun 14 - Sat 20 May 2023 Melbourne, Australia
Thu 18 May 2023 11:15 - 11:30 at Meeting Room 102 - AI testing 1 Chair(s): Matthew B Dwyer

Deep learning (DL) has attracted wide attention and has been widely deployed in recent years. As a result, more and more research efforts have been dedicated to testing DL libraries and frameworks. However, existing work largely overlooks one crucial component of any DL system, automatic differentiation (AD), which is the basis for the recent development of DL. To this end, we propose $\nabla$Fuzz, the first general and practical approach specifically targeting the critical AD component in DL libraries. Our key insight is that each DL library API can be abstracted into a function processing tensors/vectors, which can be differentially tested under various execution scenarios (for computing outputs/gradients with different implementations). We have implemented $\nabla$Fuzz as a fully automated API-level fuzzer targeting AD in DL libraries, which utilizes differential testing on different execution scenarios to test both first-order and high-order gradients, and also includes automated filtering strategies to remove false positives caused by numerical instability. We have performed an extensive study on four of the most popular and actively-maintained DL libraries, PyTorch, TensorFlow, JAX, and OneFlow. The result shows that $\nabla$Fuzz substantially outperforms state-of-the-art fuzzers in terms of both code coverage and bug detection. To date, $\nabla$Fuzz has detected 173 bugs for the studied DL libraries, with 144 already confirmed by developers (117 of which are previously unknown bugs and 107 are related to AD). None of the confirmed AD bugs were detected by existing fuzzers.

Thu 18 May

Displayed time zone: Hobart change

11:00 - 12:30
11:00
15m
Talk
When and Why Test Generators for Deep Learning Produce Invalid Inputs: an Empirical Study
Technical Track
Vincenzo Riccio University of Udine, Paolo Tonella USI Lugano
Pre-print
11:15
15m
Talk
Fuzzing Automatic Differentiation in Deep-Learning Libraries
Technical Track
Chenyuan Yang University of Illinois at Urbana-Champaign, Yinlin Deng University of Illinois at Urbana-Champaign, Jiayi Yao The Chinese University of Hong Kong, Shenzhen, Yuxing Tu Huazhong University of Science and Technology, Hanchi Li University of Science and Technology of China, Lingming Zhang University of Illinois at Urbana-Champaign
11:30
15m
Talk
Lightweight Approaches to DNN Regression Error Reduction: An Uncertainty Alignment Perspective
Technical Track
Zenan Li Nanjing University, China, Maorun Zhang Nanjing University, China, Jingwei Xu , Yuan Yao Nanjing University, Chun Cao Nanjing University, Taolue Chen Birkbeck University of London, Xiaoxing Ma Nanjing University, Jian Lu Nanjing University
Pre-print
11:45
7m
Talk
DeepJudge: A Testing Framework for Copyright Protection of Deep Learning Models
DEMO - Demonstrations
Jialuo Chen Zhejiang University, Youcheng Sun The University of Manchester, Jingyi Wang Zhejiang University, Peng Cheng Zhejiang University, Xingjun Ma Deakin University
11:52
7m
Talk
DeepCrime: from Real Faults to Mutation Testing Tool for Deep Learning
DEMO - Demonstrations
Nargiz Humbatova USI Lugano, Gunel Jahangirova King's College London, Paolo Tonella USI Lugano
12:00
7m
Talk
DiverGet: a Search-Based Software Testing approach for Deep Neural Network Quantization assessment
Journal-First Papers
Ahmed Haj Yahmed École Polytechnique de Montréal, Houssem Ben Braiek École Polytechnique de Montréal, Foutse Khomh Polytechnique Montréal, Sonia Bouzidi National Institute of Applied Science and Technology, Rania Zaatour Potsdam Institute for Climate Impact Research
12:07
15m
Talk
Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion
Technical Track
Yuanyuan Yuan The Hong Kong University of Science and Technology, Qi Pang HKUST, Shuai Wang Hong Kong University of Science and Technology