A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability
暂无分享,去创建一个
Daniel Kroening | Xinping Yi | Xiaowei Huang | Min Wu | Youcheng Sun | Emese Thamo | Marta Kwiatkowska | Wenjie Ruan | D. Kroening | Youcheng Sun | James Sharp | Xiaowei Huang | Xinping Yi | Wenjie Ruan | Min Wu | Emese Thamo
[1] John Schulman,et al. Concrete Problems in AI Safety , 2016, ArXiv.
[2] David D. Cox,et al. On the information bottleneck theory of deep learning , 2018, ICLR.
[3] Edmund M. Clarke,et al. Counterexample-Guided Abstraction Refinement , 2000, CAV.
[4] Wen-Chuan Lee,et al. MODE: automated neural network model debugging via state differential analysis and input selection , 2018, ESEC/SIGSOFT FSE.
[5] Martin Wattenberg,et al. SmoothGrad: removing noise by adding noise , 2017, ArXiv.
[6] Chih-Hong Cheng,et al. Runtime Monitoring Neuron Activation Patterns , 2018, 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE).
[7] Mingyan Liu,et al. Spatially Transformed Adversarial Examples , 2018, ICLR.
[8] Naftali Tishby,et al. The information bottleneck method , 2000, ArXiv.
[9] Le Song,et al. Learning to Explain: An Information-Theoretic Perspective on Model Interpretation , 2018, ICML.
[10] Carlos Guestrin,et al. "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.
[11] Alan L. Yuille,et al. Mitigating adversarial effects through randomization , 2017, ICLR.
[12] Xiaowei Huang,et al. Test Metrics for Recurrent Neural Networks , 2019, ArXiv.
[13] Abhishek Das,et al. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).
[14] J Hayhurst Kelly,et al. A Practical Tutorial on Modified Condition/Decision Coverage , 2001 .
[15] Xiaowei Huang,et al. Reachability Analysis of Deep Neural Networks with Provable Guarantees , 2018, IJCAI.
[16] H. Tsukimoto,et al. Rule extraction from neural networks via decision tree induction , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).
[17] Saibal Mukhopadhyay,et al. Cascade Adversarial Machine Learning Regularized with a Unified Embedding , 2017, ICLR.
[18] Geoffrey E. Hinton,et al. Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.
[19] Jian Sun,et al. Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[20] Isay Katsman,et al. Generative Adversarial Perturbations , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.
[21] Hong Liu,et al. Universal Perturbation Attack Against Image Retrieval , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).
[22] Thomas Brox,et al. Inverting Convolutional Networks with Convolutional Networks , 2015, ArXiv.
[23] Eneldo Loza Mencía,et al. DeepRED - Rule Extraction from Deep Neural Networks , 2016, DS.
[24] Sarfraz Khurshid,et al. Symbolic Execution for Deep Neural Networks , 2018, ArXiv.
[25] Yifan Zhou,et al. Reliability Validation of Learning Enabled Vehicle Tracking , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).
[26] Li Fei-Fei,et al. Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.
[27] Graham W. Taylor,et al. Learning Confidence for Out-of-Distribution Detection in Neural Networks , 2018, ArXiv.
[28] Chung-Hao Huang,et al. Quantitative Projection Coverage for Testing ML-enabled Autonomous Systems , 2018, ATVA.
[29] Eran Yahav,et al. Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples , 2017, ICML.
[30] Geoffrey E. Hinton,et al. Distilling the Knowledge in a Neural Network , 2015, ArXiv.
[31] Ming-Yu Liu,et al. Tactics of Adversarial Attack on Deep Reinforcement Learning Agents , 2017, IJCAI.
[32] Rob Fergus,et al. Visualizing and Understanding Convolutional Networks , 2013, ECCV.
[33] Mark Harman,et al. An Analysis and Survey of the Development of Mutation Testing , 2011, IEEE Transactions on Software Engineering.
[34] Scott Lundberg,et al. A Unified Approach to Interpreting Model Predictions , 2017, NIPS.
[35] Tom Schaul,et al. Dueling Network Architectures for Deep Reinforcement Learning , 2015, ICML.
[36] Xiaowei Huang,et al. Reasoning about Cognitive Trust in Stochastic Multiagent Systems , 2017, AAAI.
[37] Mykel J. Kochenderfer,et al. Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks , 2017, CAV.
[38] Thomas Brox,et al. Universal Adversarial Perturbations Against Semantic Image Segmentation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).
[39] Guigang Zhang,et al. Deep Learning , 2016, Int. J. Semantic Comput..
[40] 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).
[41] Avanti Shrikumar,et al. Learning Important Features Through Propagating Activation Differences , 2017, ICML.
[42] Deborah Silver,et al. Feature Visualization , 1994, Scientific Visualization.
[43] Moustapha Cissé,et al. Countering Adversarial Images using Input Transformations , 2018, ICLR.
[44] Matthias Hein,et al. Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation , 2017, NIPS.
[45] J. H. Davis,et al. An Integrative Model Of Organizational Trust , 1995 .
[46] 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).
[47] Kamyar Azizzadenesheli,et al. Stochastic Activation Pruning for Robust Adversarial Defense , 2018, ICLR.
[48] Yue Zhao,et al. DLFuzz: differential fuzzing testing of deep learning systems , 2018, ESEC/SIGSOFT FSE.
[49] Jimmy Ba,et al. Adam: A Method for Stochastic Optimization , 2014, ICLR.
[50] Pushmeet Kohli,et al. A Dual Approach to Scalable Verification of Deep Networks , 2018, UAI.
[51] Michael E. Houle,et al. Local Intrinsic Dimensionality I: An Extreme-Value-Theoretic Foundation for Similarity Applications , 2017, SISAP.
[52] Dana Angluin,et al. Learning Regular Sets from Queries and Counterexamples , 1987, Inf. Comput..
[53] Sudipta Chattopadhyay,et al. Automated Directed Fairness Testing , 2018, 2018 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE).
[54] Helmut Veith,et al. Counterexample-guided abstraction refinement for symbolic model checking , 2003, JACM.
[55] Chung-Hao Huang,et al. nn-dependability-kit: Engineering Neural Networks for Safety-Critical Systems , 2018, ArXiv.
[56] David A. Forsyth,et al. NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles , 2017, ArXiv.
[57] Farinaz Koushanfar,et al. Universal Adversarial Perturbations for Speech Recognition Systems , 2019, INTERSPEECH.
[58] J. Zico Kolter,et al. Provable defenses against adversarial examples via the convex outer adversarial polytope , 2017, ICML.
[59] Alessio Lomuscio,et al. An approach to reachability analysis for feed-forward ReLU neural networks , 2017, ArXiv.
[60] Patrick Cousot,et al. Abstract interpretation: a unified lattice model for static analysis of programs by construction or approximation of fixpoints , 1977, POPL.
[61] David A. Wagner,et al. Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).
[62] Nina Narodytska,et al. Formal Analysis of Deep Binarized Neural Networks , 2018, IJCAI.
[63] Francisco Herrera,et al. A unifying view on dataset shift in classification , 2012, Pattern Recognit..
[64] Aleksander Madry,et al. Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.
[65] Xiaowei Huang,et al. testRNN: Coverage-guided Testing on Recurrent Neural Networks , 2019, ArXiv.
[66] John C. Duchi,et al. Certifying Some Distributional Robustness with Principled Adversarial Training , 2017, ICLR.
[67] Zhou Wang,et al. Multiscale structural similarity for image quality assessment , 2003, The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003.
[68] Hang Su,et al. Sparse Adversarial Perturbations for Videos , 2018, AAAI.
[69] Lei Ma,et al. DeepGauge: Comprehensive and Multi-Granularity Testing Criteria for Gauging the Robustness of Deep Learning Systems , 2018, ArXiv.
[70] Shane Legg,et al. Human-level control through deep reinforcement learning , 2015, Nature.
[71] Percy Liang,et al. Understanding Black-box Predictions via Influence Functions , 2017, ICML.
[72] Kevin Gimpel,et al. Early Methods for Detecting Adversarial Images , 2016, ICLR.
[73] Matthew Wicker,et al. Feature-Guided Black-Box Safety Testing of Deep Neural Networks , 2017, TACAS.
[74] Ramprasaath R. Selvaraju,et al. Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization , 2016 .
[75] Ryan R. Curtin,et al. Detecting Adversarial Samples from Artifacts , 2017, ArXiv.
[76] Yannic Noller,et al. HyDiff: Hybrid Differential Software Analysis , 2020, 2020 IEEE/ACM 42nd International Conference on Software Engineering (ICSE).
[77] Klaus-Robert Müller,et al. Explainable artificial intelligence , 2017 .
[78] Ryen W. White. Opportunities and challenges in search interaction , 2018, Commun. ACM.
[79] Jonathon Shlens,et al. Explaining and Harnessing Adversarial Examples , 2014, ICLR.
[80] Alberto L. Sangiovanni-Vincentelli,et al. Systematic Testing of Convolutional Neural Networks for Autonomous Driving , 2017, ArXiv.
[81] Sven Gowal,et al. Scalable Verified Training for Provably Robust Image Classification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).
[82] Percy Liang,et al. Certified Defenses for Data Poisoning Attacks , 2017, NIPS.
[83] Rama Chellappa,et al. Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models , 2018, ICLR.
[84] Yifan Zhou,et al. Formal Verification of Robustness and Resilience of Learning-Enabled State Estimation Systems for Robotics , 2020, ArXiv.
[85] Ananthram Swami,et al. Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks , 2015, 2016 IEEE Symposium on Security and Privacy (SP).
[86] Zhendong Su,et al. A Survey on Data-Flow Testing , 2017, ACM Comput. Surv..
[87] Max Welling,et al. Visualizing Deep Neural Network Decisions: Prediction Difference Analysis , 2017, ICLR.
[88] R. Venkatesh Babu,et al. Generalizable Data-Free Objective for Crafting Universal Adversarial Perturbations , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.
[89] Pushmeet Kohli,et al. Piecewise Linear Neural Network verification: A comparative study , 2017, ArXiv.
[90] Cengiz Öztireli,et al. Towards better understanding of gradient-based attribution methods for Deep Neural Networks , 2017, ICLR.
[91] Yvan Saeys,et al. Lower bounds on the robustness to adversarial perturbations , 2017, NIPS.
[92] Chih-Hong Cheng,et al. Maximum Resilience of Artificial Neural Networks , 2017, ATVA.
[93] Daniel Kroening,et al. Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the Hamming Distance , 2019, IJCAI.
[94] Junfeng Yang,et al. Towards Practical Verification of Machine Learning: The Case of Computer Vision Systems , 2017, ArXiv.
[95] Sandy H. Huang,et al. Adversarial Attacks on Neural Network Policies , 2017, ICLR.
[96] Seong Joon Oh,et al. Sequential Attacks on Agents for Long-Term Adversarial Goals , 2018, ArXiv.
[97] Luca Pulina,et al. An Abstraction-Refinement Approach to Verification of Artificial Neural Networks , 2010, CAV.
[98] Bernhard C. Geiger,et al. How (Not) To Train Your Neural Network Using the Information Bottleneck Principle , 2018, ArXiv.
[99] Seyed-Mohsen Moosavi-Dezfooli,et al. Universal Adversarial Perturbations , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[100] Ananthram Swami,et al. The Limitations of Deep Learning in Adversarial Settings , 2015, 2016 IEEE European Symposium on Security and Privacy (EuroS&P).
[101] Michael S. Bernstein,et al. ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.
[102] George Danezis,et al. Learning Universal Adversarial Perturbations with Generative Models , 2017, 2018 IEEE Security and Privacy Workshops (SPW).
[103] Jian Pei,et al. Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solution , 2018, KDD.
[104] Yanjun Qi,et al. Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks , 2017, NDSS.
[105] C. Lee Giles,et al. Extraction of rules from discrete-time recurrent neural networks , 1996, Neural Networks.
[106] Junfeng Yang,et al. DeepXplore: Automated Whitebox Testing of Deep Learning Systems , 2017, SOSP.
[107] Jianjun Zhao,et al. DeepStellar: model-based quantitative analysis of stateful deep learning systems , 2019, ESEC/SIGSOFT FSE.
[108] Geoffrey E. Hinton,et al. Deep Learning , 2015, Nature.
[109] Tom Schaul,et al. Prioritized Experience Replay , 2015, ICLR.
[110] Naftali Tishby,et al. Opening the Black Box of Deep Neural Networks via Information , 2017, ArXiv.
[111] Joseph Sifakis,et al. Autonomous Systems - An Architectural Characterization , 2018, Models, Languages, and Tools for Concurrent and Distributed Programming.
[112] Agustí Verde Parera,et al. General data protection regulation , 2018 .
[113] Samy Bengio,et al. Adversarial examples in the physical world , 2016, ICLR.
[114] Christian Gagné,et al. Controlling Over-generalization and its Effect on Adversarial Examples Generation and Detection , 2018, ArXiv.
[115] Andrew Zisserman,et al. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.
[116] Joan Bruna,et al. Intriguing properties of neural networks , 2013, ICLR.
[117] Andrew L. Beam,et al. Adversarial Attacks Against Medical Deep Learning Systems , 2018, ArXiv.
[118] Paul Voosen,et al. How AI detectives are cracking open the black box of deep learning , 2017 .
[119] Jason Weston,et al. Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..
[120] David Silver,et al. Deep Reinforcement Learning with Double Q-Learning , 2015, AAAI.
[121] John C. Duchi,et al. Certifiable Distributional Robustness with Principled Adversarial Training , 2017, ArXiv.
[122] Swarat Chaudhuri,et al. AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation , 2018, 2018 IEEE Symposium on Security and Privacy (SP).
[123] Carlos Guestrin,et al. Anchors: High-Precision Model-Agnostic Explanations , 2018, AAAI.
[124] Yang Song,et al. PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples , 2017, ICLR.
[125] Fabio Roli,et al. Evasion Attacks against Machine Learning at Test Time , 2013, ECML/PKDD.
[126] Diptikalyan Saha,et al. Automated Test Generation to Detect Individual Discrimination in AI Models , 2018, ArXiv.
[127] Min Wu,et al. Safety Verification of Deep Neural Networks , 2016, CAV.
[128] Chung-Hao Huang,et al. Towards Dependability Metrics for Neural Networks , 2018, 2018 16th ACM/IEEE International Conference on Formal Methods and Models for System Design (MEMOCODE).
[129] lawa Kanas,et al. Metric Spaces , 2020, An Introduction to Functional Analysis.
[130] Alex Graves,et al. Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.
[131] Jun Wan,et al. MuNN: Mutation Analysis of Neural Networks , 2018, 2018 IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C).
[132] Rick Salay,et al. Using Machine Learning Safely in Automotive Software: An Assessment and Adaption of Software Process Requirements in ISO 26262 , 2018, ArXiv.
[133] Demis Hassabis,et al. Mastering the game of Go without human knowledge , 2017, Nature.
[134] Andrea Vedaldi,et al. Interpretable Explanations of Black Boxes by Meaningful Perturbation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).
[135] Ian Goodfellow,et al. TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing , 2018, ICML.
[136] Colin Raffel,et al. Thermometer Encoding: One Hot Way To Resist Adversarial Examples , 2018, ICLR.
[137] Dan Boneh,et al. Ensemble Adversarial Training: Attacks and Defenses , 2017, ICLR.
[138] David A. Wagner,et al. MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples , 2017, ArXiv.
[139] Hong Zhu,et al. Software unit test coverage and adequacy , 1997, ACM Comput. Surv..
[140] Yarin Gal,et al. Real Time Image Saliency for Black Box Classifiers , 2017, NIPS.
[141] Liqian Chen,et al. Analyzing Deep Neural Networks with Symbolic Propagation: Towards Higher Precision and Faster Verification , 2019, SAS.
[142] Yoshua Bengio,et al. Generative Adversarial Nets , 2014, NIPS.
[143] Hod Lipson,et al. Understanding Neural Networks Through Deep Visualization , 2015, ArXiv.
[144] R. Srikant,et al. Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks , 2017, ICLR.
[145] Matthew Hill,et al. "Boxing Clever": Practical Techniques for Gaining Insights into Training Data and Monitoring Distribution Shift , 2018, SAFECOMP Workshops.
[146] Aleksander Madry,et al. A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations , 2017, ArXiv.
[147] Hoyt Lougee,et al. SOFTWARE CONSIDERATIONS IN AIRBORNE SYSTEMS AND EQUIPMENT CERTIFICATION , 2001 .
[148] Vittoria Bruni,et al. An entropy based approach for SSIM speed up , 2017, Signal Process..
[149] Zachary Chase Lipton. The mythos of model interpretability , 2016, ACM Queue.
[150] Min Wu,et al. A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees , 2018, Theor. Comput. Sci..
[151] A. Jefferson Offutt,et al. Introduction to Software Testing , 2008 .
[152] Aditi Raghunathan,et al. Certified Defenses against Adversarial Examples , 2018, ICLR.
[153] Ian J. Goodfellow,et al. Technical Report on the CleverHans v2.1.0 Adversarial Examples Library , 2016 .
[154] Prateek Mittal,et al. Dimensionality Reduction as a Defense against Evasion Attacks on Machine Learning Classifiers , 2017, ArXiv.
[155] Cho-Jui Hsieh,et al. Efficient Neural Network Robustness Certification with General Activation Functions , 2018, NeurIPS.
[156] David Flynn,et al. A Safety Framework for Critical Systems Utilising Deep Neural Networks , 2020, SAFECOMP.
[157] Daniel Kroening,et al. Concolic Testing for Deep Neural Networks , 2018, 2018 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE).
[158] Sarfraz Khurshid,et al. DeepRoad: GAN-based Metamorphic Autonomous Driving System Testing , 2018, ArXiv.
[159] Thomas Brox,et al. Striving for Simplicity: The All Convolutional Net , 2014, ICLR.
[160] Leonid Ryzhyk,et al. Verifying Properties of Binarized Deep Neural Networks , 2017, AAAI.
[161] Matthew Mirman,et al. Differentiable Abstract Interpretation for Provably Robust Neural Networks , 2018, ICML.
[162] Weiming Xiang,et al. Output Reachable Set Estimation and Verification for Multilayer Neural Networks , 2017, IEEE Transactions on Neural Networks and Learning Systems.
[163] Inderjit S. Dhillon,et al. Towards Fast Computation of Certified Robustness for ReLU Networks , 2018, ICML.
[164] Jan Hendrik Metzen,et al. On Detecting Adversarial Perturbations , 2017, ICLR.
[165] Cho-Jui Hsieh,et al. RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications , 2018, AAAI.
[166] Thomas Brox,et al. U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.
[167] Shin Yoo,et al. Guiding Deep Learning System Testing Using Surprise Adequacy , 2018, 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE).
[168] Lei Ma,et al. DeepMutation: Mutation Testing of Deep Learning Systems , 2018, 2018 IEEE 29th International Symposium on Software Reliability Engineering (ISSRE).
[169] Matthew P. Wand,et al. Kernel Smoothing , 1995 .
[170] Alexander Binder,et al. On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.
[171] Martin Wattenberg,et al. Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) , 2017, ICML.
[172] Xiaoxing Ma,et al. Manifesting Bugs in Machine Learning Code: An Explorative Study with Mutation Testing , 2018, 2018 IEEE International Conference on Software Quality, Reliability and Security (QRS).
[173] Lei Ma,et al. DeepHunter: Hunting Deep Neural Network Defects via Coverage-Guided Fuzzing , 2018, 1809.01266.
[174] Edmund M. Clarke,et al. Counterexample-guided abstraction refinement , 2003, 10th International Symposium on Temporal Representation and Reasoning, 2003 and Fourth International Conference on Temporal Logic. Proceedings..
[175] Ö. Özer,et al. Trust and Trustworthiness , 2017, The Handbook of Behavioral Operations.
[176] Ian J. Goodfellow. Gradient Masking Causes CLEVER to Overestimate Adversarial Perturbation Size , 2018, ArXiv.
[177] Daniel Kroening,et al. Testing Deep Neural Networks , 2018, ArXiv.
[178] Hao Chen,et al. MagNet: A Two-Pronged Defense against Adversarial Examples , 2017, CCS.
[179] Daniel Kroening,et al. Structural Test Coverage Criteria for Deep Neural Networks , 2019, 2019 IEEE/ACM 41st International Conference on Software Engineering: Companion Proceedings (ICSE-Companion).
[180] Dejing Dou,et al. HotFlip: White-Box Adversarial Examples for Text Classification , 2017, ACL.
[181] Yadong Wang,et al. Combinatorial Testing for Deep Learning Systems , 2018, ArXiv.
[182] Arnold Neumaier,et al. Safe bounds in linear and mixed-integer linear programming , 2004, Math. Program..
[183] Girish Chowdhary,et al. Robust Deep Reinforcement Learning with Adversarial Attacks , 2017, AAMAS.
[184] Natalie Wolchover,et al. New Theory Cracks Open the Black Box of Deep Learning , 2017 .
[185] Enrico Bertini,et al. Interpreting Black-Box Classifiers Using Instance-Level Visual Explanations , 2017, HILDA@SIGMOD.
[186] Stephan Merz,et al. Model Checking , 2000 .
[187] Jinfeng Yi,et al. Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach , 2018, ICLR.
[188] Andrea Vedaldi,et al. Understanding deep image representations by inverting them , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[189] Ashish Tiwari,et al. Output Range Analysis for Deep Neural Networks , 2017, ArXiv.
[190] Pascal Vincent,et al. Visualizing Higher-Layer Features of a Deep Network , 2009 .
[191] Roderick Bloem,et al. Repair with On-The-Fly Program Analysis , 2012, Haifa Verification Conference.
[192] Daniel Kroening,et al. Structural Test Coverage Criteria for Deep Neural Networks , 2019, ACM Trans. Embed. Comput. Syst..
[193] Rüdiger Ehlers,et al. Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks , 2017, ATVA.
[194] Daniel Kroening,et al. DeepConcolic: Testing and Debugging Deep Neural Networks , 2019, 2019 IEEE/ACM 41st International Conference on Software Engineering: Companion Proceedings (ICSE-Companion).
[195] Sepp Hochreiter,et al. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.
[196] Brian Kingsbury,et al. Estimating Information Flow in Neural Networks , 2018, ArXiv.
[197] James Bailey,et al. Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality , 2018, ICLR.
[198] Ankur Taly,et al. Axiomatic Attribution for Deep Networks , 2017, ICML.
[199] John Rushby,et al. The Interpretation and Evaluation of Assurance Cases , 2015 .
[200] Junfeng Yang,et al. Formal Security Analysis of Neural Networks using Symbolic Intervals , 2018, USENIX Security Symposium.
[201] Antonio Criminisi,et al. Measuring Neural Net Robustness with Constraints , 2016, NIPS.
[202] David Wagner,et al. Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods , 2017, AISec@CCS.