{"type":"ScholarlyArticle","title":"DiffChaser: Detecting Disagreements for Deep Neural Networks","authors":[{"name":"Xiaofei Xie","slug":"xiaofei-xie","given":"Xiaofei","family":"Xie","affiliation":"Nanyang Technological University , Singapore"},{"name":"Lei Ma","slug":"lei-ma","given":"Lei","family":"Ma","affiliation":"Kyushu University , Japan"},{"name":"Haijun Wang","slug":"haijun-wang","given":"Haijun","family":"Wang","affiliation":"Nanyang Technological University , Singapore"},{"name":"Yuekang Li","slug":"yuekang-li","given":"Yuekang","family":"Li","affiliation":"Nanyang Technological University , Singapore"},{"name":"Yang Liu","slug":"yang-liu","given":"Yang","family":"Liu","affiliation":"Nanyang Technological University , Singapore; Zhejiang Sci-Tech University , China"},{"name":"Xiaohong Li","slug":"xiaohong-li","given":"Xiaohong","family":"Li","affiliation":"Tianjin University , China"}],"abstract":"The platform migration and customization have become an indispensable process of deep neural network (DNN) development lifecycle. A high-precision but complex DNN trained in the cloud on massive data and powerful GPUs often goes through an optimization phase (e.g, quantization, compression) before deployment to a target device (e.g, mobile device). A test set that effectively uncovers the disagreements of a DNN and its optimized variant provides certain feedback to debug and further enhance the optimization procedure. However, the minor inconsistency between a DNN and its optimized version is often hard to detect and easily bypasses the original test set. This paper proposes DiffChaser, an automated black-box testing framework to detect untargeted/targeted disagreements between version variants of a DNN. We demonstrate 1) its effectiveness by comparing with the state-of-the-art techniques, and 2) its usefulness in real-world DNN product deployment involved with quantization and optimization.","doi":"10.24963/ijcai.2019/800","url":"https://ijcai.org/proceedings/2019/800","pdf":"https://ijcai.org/proceedings/2019/0800.pdf","markdown":"https://ijcai.org/proceedings/2019/800.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/800","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Uncertainty in AI","track":"Main track","number":800,"pages":{"first":5772,"last":5778},"keywords":["Machine Learning: Adversarial Machine Learning","Uncertainty in AI: Uncertainty Representations"],"videos":[],"references":[{"position":1,"raw":"[Carlini and Wagner, 2017] Nicholas Carlini and David Wagner. Towards evaluating the robustness of neural networks. In IEEE Symposium on Security and Privacy (S&P), pages 39-57, May 2017.","title":"Towards evaluating the robustness of neural networks","authors":"Wagner Carlini, Nicholas Carlini, David Wagner","year":"2017","venue":"IEEE Symposium on Security and Privacy (S&P)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cheng et al., 2017] Yu Cheng, Duo Wang, Pan Zhou, and Tao Zhang. A survey of model compression and ac- celeration for deep neural networks. arXiv preprint arXiv:1710.09282, 2017.","title":"A survey of model compression and acceleration for deep neural networks","authors":"Yu Cheng, Duo Wang, Pan Zhou, Tao Zhang","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ciregan et al., 2012] Dan Ciregan, Ueli Meier, and Jürgen Schmidhuber. Multi-column deep neural networks for im- age classification. In CVPR, pages 3642-3649, 2012.","title":"Multi-column deep neural networks for image classification","authors":"Dan Ciregan, Ueli Meier, Jürgen Schmidhuber","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Du et al., 2019] Xiaoning Du, Xiaofei Xie, Yi Li, Lei Ma, Yang Liu, and Jianjun Zhao. Deepstellar: Model-based quantitative analysis of stateful deep learning systems. In The 27th ACM Joint European Software Engineering Con- ference and Symposium on the Foundations of Software Engineering, 2019.","title":"Deepstellar: Model-based quantitative analysis of stateful deep learning systems","authors":"Xiaoning Du, Xiaofei Xie, Yi Li, Lei Ma, Yang Liu, Jianjun Zhao","year":"2019","venue":"The 27th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gal and Ghahramani, 2016] Yarin Gal and Zoubin Ghahra- mani. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international con- ference on machine learning, pages 1050-1059, 2016.","title":"Yarin Gal and Zoubin Ghahramani. Dropout as a bayesian approximation: Representing model uncertainty in deep learning","authors":"Ghahramani Gal","year":"2016","venue":"international conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Goodfellow et al., 2015] Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and harnessing adversarial examples. In ICLR, 2015.","title":"Explaining and harnessing adversarial examples","authors":"Ian J Goodfellow, Jonathon Shlens, Christian Szegedy","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hinton et al., 2012] Geoffrey Hinton, Li Deng, Dong Yu, George E Dahl, Abdel-rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N Sainath, et al. Deep Neural Networks for Acous- tic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE Signal Processing Maga- zine, 29(6):82-97, 2012.","title":"Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups","authors":"Geoffrey Hinton, Li Deng, Dong Yu, George E Dahl, Abdel-Rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N Sainath","year":"2012","venue":"IEEE Signal Processing Magazine","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Huval et al., 2015] Brody Huval, Tao Wang, Sameep Tan- don, Jeff Kiske, Will Song, Joel Pazhayampallil, Mykhaylo Andriluka, Pranav Rajpurkar, Toki Migimatsu, Royce Cheng-Yue, Fernando Mujica, Adam Coates, and Andrew Y. Ng. An empirical evaluation of deep learning on highway driving. CoRR, abs/1504.01716, 2015.","title":"An empirical evaluation of deep learning on highway driving","authors":"Brody Huval, Tao Wang, Sameep Tandon, Jeff Kiske, Will Song, Joel Pazhayampallil, Mykhaylo Andriluka, Pranav Rajpurkar, Toki Migimatsu, Royce Cheng-Yue, Fernando Mujica, Adam Coates, Andrew Y Ng","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Krizhevsky et al., 2014] Nair Krizhevsky, Hinton Vinod, Christopher Geoffrey, Mike Papadakis, and Anthony Ven- tresque. The cifar-10 dataset. http://www.cs.toronto.edu/ kriz/cifar.html, 2014.","title":"The cifar-10 dataset","authors":"Nair Krizhevsky, Hinton Vinod, Christopher Geoffrey, Mike Papadakis, Anthony Ventresque","year":null,"venue":null,"doi":null,"url":"http://www.cs.toronto.edu/kriz/cifar.html,2014","internal_url":null},{"position":11,"raw":"[Kurakin et al., 2017] Alexey Kurakin, Ian Goodfellow, and Samy Bengio. Adversarial examples in the physical world. ICLR, 2017.","title":"Adversarial examples in the physical world","authors":"Alexey Kurakin, Ian Goodfellow, Samy Bengio","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[LeCun and Cortes, 1998] Yann LeCun and Corrina Cortes. The MNIST database of handwritten digits, 1998.","title":"The MNIST database of handwritten digits","authors":"Lecun, Cortes, Yann Lecun, Corrina Cortes","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[LeCun et al., 1998] Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proc. of the IEEE, 86(11):2278-2324, 1998.","title":"Gradient-based learning applied to document recognition","authors":"Yann Lecun, Léon Bottou, Yoshua Bengio, Patrick Haffner","year":"1998","venue":"Proc. of the IEEE","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ma et al., 2018a] Lei Ma, Felix Juefei-Xu, Jiyuan Sun, Chunyang Chen, Ting Su, Fuyuan Zhang, Minhui Xue, Bo Li, Li Li, Yang Liu, et al. Deepgauge: Multi- granularity testing criteria for deep learning systems. The 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE 2018), 2018.","title":"Deepgauge: Multigranularity testing criteria for deep learning systems","authors":"Ma","year":"2018","venue":"The 33rd IEEE/ACM International Conference on Automated Software Engineering","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ma et al., 2018b] Lei Ma, Fuyuan Zhang, Jiyuan Sun, Min- hui Xue, Bo Li, Felix Juefei-Xu, Chao Xie, Li Li, Yang Liu, Jianjun Zhao, et al. Deepmutation: Mutation testing of deep learning systems. In 2018 IEEE 29th International Symposium on Software Reliability Engineering (ISSRE), pages 100-111. IEEE, 2018.","title":"Deepmutation: Mutation testing of deep learning systems","authors":"Ma","year":"2018","venue":"IEEE 29th International Symposium on Software Reliability Engineering (ISSRE)","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ma et al., 2019] Lei Ma, Felix Juefei-Xu, Minhui Xue, Bo Li, Li Li, Yang Liu, and Jianjun Zhao. Deepct: Tomo- graphic combinatorial testing for deep learning systems. In 2019 IEEE 26th International Conference on Software Analysis, Evolution and Reengineering (SANER), pages 614-618. IEEE, 2019.","title":"Deepct: Tomographic combinatorial testing for deep learning systems","authors":"Lei Ma, Felix Juefei-Xu, Minhui Xue, Bo Li, Li Li, Yang Liu, Jianjun Zhao","year":"2019","venue":"IEEE 26th International Conference on Software Analysis, Evolution and Reengineering (SANER)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mitchell, 1998] Melanie Mitchell. An introduction to ge- netic algorithms. MIT press, 1998.","title":"An introduction to genetic algorithms","authors":"Melanie Mitchell","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Odena and Goodfellow, 2018] Augustus Odena and Ian Goodfellow. Tensorfuzz: Debugging neural net- works with coverage-guided fuzzing. arXiv preprint arXiv:1807.10875, 2018.","title":"Augustus Odena and Ian Goodfellow. Tensorfuzz: Debugging neural networks with coverage-guided fuzzing","authors":"Goodfellow Odena","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Papernot et al., 2016] Nicolas Papernot, Patrick McDaniel, Somesh Jha, Matt Fredrikson, Z Berkay Celik, and Anan- thram Swami. The limitations of deep learning in adver- sarial settings. In Security and Privacy (EuroS&P), 2016 IEEE European Symposium on, pages 372-387. IEEE, 2016.","title":"The limitations of deep learning in adversarial settings","authors":"Nicolas Papernot, Patrick Mcdaniel, Somesh Jha, Matt Fredrikson, Z Berkay Celik, Ananthram Swami","year":"2016","venue":"Security and Privacy (EuroS&P)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pei et al., 2017] Kexin Pei, Yinzhi Cao, Junfeng Yang, and Suman Jana. Deepxplore: Automated whitebox testing of deep learning systems. In Proceedings of the 26th Sympo- sium on Operating Systems Principles, pages 1-18, 2017.","title":"Deepxplore: Automated whitebox testing of deep learning systems","authors":"Kexin Pei, Yinzhi Cao, Junfeng Yang, Suman Jana","year":"2017","venue":"Proceedings of the 26th Symposium on Operating Systems Principles","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Polino et al., 2018] Antonio Polino, Razvan Pascanu, and Dan Alistarh. Model compression via distillation and quantization. arXiv preprint arXiv:1802.05668, 2018.","title":"Model compression via distillation and quantization","authors":"Polino","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tian et al., 2018] Yuchi Tian, Kexin Pei, Suman Jana, and Baishakhi Ray. Deeptest: Automated testing of deep- neural-network-driven autonomous cars. In Proceedings of the 40th International Conference on Software Engi- neering, pages 303-314. ACM, 2018.","title":"Deeptest: Automated testing of deepneural-network-driven autonomous cars","authors":"Yuchi Tian, Kexin Pei, Suman Jana, Baishakhi Ray","year":"2018","venue":"Proceedings of the 40th International Conference on Software Engineering","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2016] Jiaxiang Wu, Cong Leng, Yuhang Wang, Qinghao Hu, and Jian Cheng. Quantized convolutional neural networks for mobile devices. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recog- nition, pages 4820-4828, 2016.","title":"Quantized convolutional neural networks for mobile devices","authors":"Jiaxiang Wu, Cong Leng, Yuhang Wang, Qinghao Hu, Jian Cheng","year":"2016","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xie et al., 2019] Xiaofei Xie, Lei Ma, Felix Juefei-Xu, Minhui Xue, Hongxu Chen, Yang Liu, Jianjun Zhao, Bo Li, Jianxiong Yin, and Simon See. Deephunter: A coverage-guided fuzz testing framework for deep neural networks. In 28th ACM SIGSOFT International Sympo- sium on Software Testing and Analysis, 2019.","title":"Deephunter: A coverage-guided fuzz testing framework for deep neural networks","authors":"Xiaofei Xie, Lei Ma, Felix Juefei-Xu, Minhui Xue, Hongxu Chen, Yang Liu, Jianjun Zhao, Bo Li, Jianxiong Yin, Simon See","year":"2019","venue":"28th ACM SIGSOFT International Symposium on Software Testing and Analysis","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}