Corner Case Data Description and Detection

As the major factors affecting the safety of deep learning models, corner cases and related detection are crucial in AI quality assurance for constructing safetyand securitycritical systems. The generic corner case researches involve two interesting topics. One is to enhance DL models’ robustness to corner case data via the adjustment on parameters/structure. The other is to generate new corner cases for model retraining and improvement. However, the complex architecture and the huge amount of parameters make the robust adjustment of DL models not easy, meanwhile it is not possible to generate all real-world corner cases for DL training. Therefore, this paper proposes a simple and novel approach aiming at corner case data detection via a specific metric. This metric is developed on surprise adequacy (SA) which has advantages on capture data behaviors. Furthermore, targeting at characteristics of corner case data, three modifications on distanced-based SA are developed for classification applications in this paper. Consequently, through the experiment analysis on MNIST data and industrial data, the feasibility and usefulness of the proposed method on corner case data detection are verified.

[1]  Yasir Malik,et al.  Is Predicting Software Security Bugs Using Deep Learning Better Than the Traditional Machine Learning Algorithms? , 2018, 2018 IEEE International Conference on Software Quality, Reliability and Security (QRS).

[2]  Aleksander Madry,et al.  Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.

[3]  Lei Ma,et al.  DeepMutation: Mutation Testing of Deep Learning Systems , 2018, 2018 IEEE 29th International Symposium on Software Reliability Engineering (ISSRE).

[4]  Tsong Yueh Chen,et al.  Generating Biased Dataset for Metamorphic Testing of Machine Learning Programs , 2019, ICTSS.

[5]  Daniel J. Rice.  The Driverless Car and the Legal System: Hopes and Fears as the Courts, Regulatory Agencies, Waymo, Tesla, and Uber Deal with this Exciting and Terrifying New Technology , 2019, Journal of Strategic Innovation and Sustainability.

[6]  Suman Jana,et al.  DeepTest: Automated Testing of Deep-Neural-Network-Driven Autonomous Cars , 2017, 2018 IEEE/ACM 40th International Conference on Software Engineering (ICSE).

[7]  R. Feldt,et al.  Reducing DNN labelling cost using surprise adequacy: an industrial case study for autonomous driving , 2020, ESEC/SIGSOFT FSE.

[8]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[9]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[10]  Sorin Grigorescu,et al.  A Survey of Deep Learning Techniques for Autonomous Driving , 2020, J. Field Robotics.

[11]  Shin Yoo,et al.  Guiding Deep Learning System Testing Using Surprise Adequacy , 2018, 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE).

[12]  Tim Fingscheidt,et al.  Towards Corner Case Detection for Autonomous Driving , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

[13]  Andrew Kusiak,et al.  Data-driven modeling of truck engine exhaust valve failures: A case study , 2017 .

[14]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Junfeng Yang,et al.  DeepXplore: Automated Whitebox Testing of Deep Learning Systems , 2017, SOSP.

[16]  Shin Yoo,et al.  Evaluating Surprise Adequacy for Question Answering , 2020, ICSE.

[17]  Khurram Kamal,et al.  An inspection approach for casting defects detection using image segmentation , 2017, 2017 International Conference on Mechanical, System and Control Engineering (ICMSC).

[18]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[19]  Samer Ellahham,et al.  Application of Artificial Intelligence in the Health Care Safety Context: Opportunities and Challenges , 2020, American journal of medical quality : the official journal of the American College of Medical Quality.

[20]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[21]  Yongqiang Lyu,et al.  Droid-Sec , 2014, SIGCOMM.

[22]  Seyed-Mohsen Moosavi-Dezfooli,et al.  DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Markus Borg,et al.  Traceability and Deep Learning - Safety-critical Systems with Traces Ending in Deep Neural Networks , 2017 .

[24]  Daniel Kroening,et al.  Testing Deep Neural Networks , 2018, ArXiv.

[25]  Weisong Shi,et al.  Edge Computing for Autonomous Driving: Opportunities and Challenges , 2019, Proceedings of the IEEE.

[26]  Weibin Wu,et al.  Deep Validation: Toward Detecting Real-World Corner Cases for Deep Neural Networks , 2019, 2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN).

[27]  Radu Banabic,et al.  Techniques for Identifying Elusive Corner-Case Bugs in Systems Software , 2015 .

[28]  Witold Pedrycz,et al.  Granular Description of Data Structures: A Two-Phase Design , 2021, IEEE Transactions on Cybernetics.

[29]  Samy Bengio,et al.  Adversarial examples in the physical world , 2016, ICLR.