… Taking steps towards debugging these issues, TensorFuzz adapts coverage-based fuzzing … debugging and providing explanations of neuralnetwork output during the training process. …
… Following standard software fuzzing, we will examine how to use SUT performance to guide mutation type and parameter selection to more quickly find inconsistencies. We will also …
… using an 8-layer convolutional neuralnetwork. Their study was to examine the effectiveness of visual posthoc model explanations in diagnosing model errors and debugging. The bugs …
Y DONG, P ZHANG, J WANG, S LIU, J SUN… - 2020 25th IEEE … - ink.library.smu.edu.sg
Deep neuralnetworks (DNN) are increasingly applied in safety-critical systems, eg, for face recognition, autonomous car control and malware detection. It is also shown that DNNs are …
… testing, file format testing or testing neuralnetworks [7], [8]. … Coverageguidedfuzzing tools (CFG) usually consist of an input mutation generator, feedback guidance, and a fuzzing …
Z Wang, S Xu, L Fan, X Cai, L Li, Z Liu - ACM Transactions on Software … - dl.acm.org
… NeuralNetwork (DNN)-based software, such as metamorphic testing [75, 97], mutation testing [57], and fuzzing [… Based on these criteria, some studies apply coverage-guidedfuzzing on …
M Wu, L Jiang, J Xiang, Y Huang, H Cui… - Proceedings of the 44th …, 2022 - dl.acm.org
… seeds, such coverageguidedfuzzers usually develop strategies … Notably, a number of recent coverage-guidedfuzzers (eg, AFL [… further use neuralnetworks to guide the fuzzing process. …
… Here DL software includes infrastructure code that performs core neuralnetwork computations and … Deephunter: a coverage-guidedfuzz testing framework for deep neuralnetworks. In …
D Berend, X Xie, L Ma, L Zhou, Y Liu, C Xu… - Proceedings of the 35th …, 2020 - dl.acm.org
… the architecture of the deep neuralnetwork (DNN), and … To test the data-driven deep neuralnetworks, a common way … Coverageguided testing is a representative and widely used …