mlsanityData to 14 Oct 2026

Neural Network Verification in Control

arXiv 2110.01388 ↗First posted 30 Sep 2021cs.LG cs.RO cs.SYcited by 14

Not on the map. Why?

Abstract (arXiv)

Learning-based methods could provide solutions to many of the long-standing challenges in control. However, the neural networks (NNs) commonly used in modern learning approaches present substantial challenges for analyzing the resulting control systems' safety properties. Fortunately, a new body of literature could provide tractable methods for analysis and verification of these high dimensional, highly nonlinear representations. This tutorial first introduces and unifies recent techniques (many of which originated in the computer vision and machine learning communities) for verifying robustness properties of NNs. The techniques are then extended to provide formal guarantees of neural feedback loops (e.g., closed-loop system with NN control policy). The provided tools are shown to enable closed-loop reachability analysis and robust deep reinforcement learning.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 55 of its 106 references that are in the map. First posted on arXiv 30 Sep 2021.

Builds on

55 of 106 references.

References · 55

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  5. 2016OpenAI Gymcited by 1,736
  6. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  7. 2016CVXPY: A Python-Embedded Modeling Language for Convex Optimizationcited by 641
  8. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 618
  9. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  10. 2017Robust Adversarial Reinforcement Learningcited by 451
  11. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
  12. 2020Lagrangian Neural Networkscited by 398
38 more
  1. 2020Universal Differential Equations for Scientific Machine Learningcited by 353
  2. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
  3. 2017Adversarial Attacks on Neural Network Policiescited by 320
  4. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
  5. 2018Certified Defenses against Adversarial Examplescited by 306
  6. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 288
  7. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 287
  8. 2016Safety Verification of Deep Neural Networkscited by 263
  9. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 255
  10. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 242
  11. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 214
  12. 2019Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learningcited by 212
  13. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 205
  14. 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 201
  15. 2018Formal Security Analysis of Neural Networks using Symbolic Intervalscited by 185
  16. 2019Soft Actor-Critic for Discrete Action Settingscited by 174
  17. 2016EPOpt: Learning Robust Neural Network Policies Using Model Ensemblescited by 138
  18. 2018Recent Advances in Autoencoder-Based Representation Learningcited by 133
  19. 2017An approach to reachability analysis for feed-forward ReLU neural networkscited by 127
  20. 2017Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systemscited by 127
  21. 2019A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networkscited by 125
  22. 2019Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programmingcited by 101
  23. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  24. 2020DeepReach: A Deep Learning Approach to High-Dimensional Reachabilitycited by 91
  25. 2018Verisig: verifying safety properties of hybrid systems with neural network controllerscited by 84
  26. 2017Output Reachable Set Estimation and Verification for Multi-Layer Neural Networkscited by 80
  27. 2020Enabling certification of verification-agnostic networks via memory-efficient semidefinite programmingcited by 66
  28. 2020Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learningcited by 61
  29. 2020The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verificationcited by 50
  30. 2020Stability Analysis using Quadratic Constraints for Systems with Neural Network Controllerscited by 44
  31. 2020Reach-SDP: Reachability Analysis of Closed-Loop Systems with Neural Network Controllers via Semidefinite Programmingcited by 43
  32. 2021Reachability Analysis of Neural Feedback Loopscited by 41
  33. 2020Reachable Set Estimation for Neural Network Control Systems: A Simulation-Guided Approachcited by 36
  34. 2020Reachable Polyhedral Marching (RPM): A Safety Verification Algorithm for Robotic Systems with Deep Neural Network Componentscited by 36
  35. 2018Verification for Machine Learning, Autonomy, and Neural Networks Surveycited by 24
  36. 2020Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learningcited by 24
  37. 2020Learning Lyapunov Functions for Hybrid Systemscited by 24
  38. 2019Fast Neural Network Verification via Shadow Pricescited by 17

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 2; 2024: 3; 2025: 3; 2026: 3.

14 papers.

Sort:

By area:

  1. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classificationcited by 26
  2. 2022Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specificationscited by 6
  3. 2022Chordal Sparsity for SDP-based Neural Network Verificationcited by 4
  4. 2024Certifying Robustness of Learning-Based Keypoint Detection and Pose Estimation Methodscited by 4
  5. 2023Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policycited by 3
  6. 2024Achieving the Tightest Relaxation of Sigmoids for Formal Verificationcited by 2
  7. 2025Deterministic World Models for Closed-loop Reachability Analysis of End-to-End Vision-based Controlcited by 2
  8. 2021Certifiable Artificial Intelligence Through Data Fusioncited by 0
  9. 2023Rational Neural Network Controllerscited by 0
  10. 2024Learning a Stable, Safe, Distributed Feedback Controller for a Heterogeneous Platoon of Autonomous Vehiclescited by 0
  11. 2025Robust Verification of Controllers under State Uncertainty via Hamilton-Jacobi Reachability Analysiscited by 0
  12. 2026From Decoupled to Coupled: Robustness Verification for Learning-based Keypoint Detection with Joint Specificationscited by 0
2 more
  1. 2026(DNN)2: Doubly Non-Negative Relaxations for Deep Neural Networkscited by 0
  2. 2026Safety Screening for Voltage Control in Active Distribution Grids via Distributionally Robust Conformal Screeningcited by 0