Towards More Complete Constraints for Deep Learning Library Testing via Complementary Set Guided Refinement

作者：Gwihwan Go, Chijin Zhou, Quan Zhang, Xiazijian Zou, Heyuan Shi, Yu Jiang · 年份：2024 · DOI：10.1145/3650212.3680364 · 被引用次数：4 · 研究领域：Adversarial Robustness in Machine Learning、Advanced Neural Network Applications、Software Testing and Debugging Techniques

Deep learning library is important in AI systems. Recently, many works have been proposed to ensure its reliability. They often model inputs of tensor operations as constraints to guide the generation of test cases. However, these constraints may narrow the search space, resulting in incomplete testing. This paper introduces a complementary set-guided refinement that can enhance the completeness of constraints. The basic idea is to see if the complementary set of constraints yields valid test cases. If so, the original constraint is incomplete and needs refinement. Based on this idea, we design an automatic constraint refinement tool, DeepConstr, which adopts a genetic algorithm to refine constraints for better completeness. We evaluated it on two DL libraries, PyTorch and TensorFlow. DeepConstr discovered 84 unknown bugs, out of which 72 were confirmed, with 51 fixed. Compared to state-of-the-art fuzzers, DeepConstr increased coverage for 43.44% of operators supported by NNSmith, and 59.16% of operators supported by NeuRI.