Estimating Neural Network Robustness via Lipschitz Constant and Architecture Sensitivity
Not on the map. Why?
Abstract (arXiv)
Ensuring neural network robustness is essential for the safe and reliable operation of robotic learning systems, especially in perception and decision-making tasks within real-world environments. This paper investigates the robustness of neural networks in perception systems, specifically examining their sensitivity to targeted, small-scale perturbations. We identify the Lipschitz constant as a key metric for quantifying and enhancing network robustness. We derive an analytical expression to compute the Lipschitz constant based on neural network architecture, providing a theoretical basis for estimating and improving robustness. Several experiments reveal the relationship between network design, the Lipschitz constant, and robustness, offering practical insights for developing safer, more robust robot learning systems.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 26 of its 38 references that are in the map. First posted on arXiv 30 Oct 2024.
Builds on
26 of 38 references.
References · 26
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2013Intriguing properties of neural networkscited by 5,155
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
- 2017Spectrally-normalized margin bounds for neural networkscited by 686
- 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
- 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 403
- 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
- 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
- 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 293
- 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 255
- 2019Algorithms for Verifying Deep Neural Networkscited by 221
14 more
- 2017Spectral Norm Regularization for Improving the Generalizability of Deep Learningcited by 182
- 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 182
- 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 144
- 2018The Limits and Potentials of Deep Learning for Roboticscited by 104
- 2019Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networkscited by 87
- 2020Lipschitz constant estimation of Neural Networks via sparse polynomial optimizationcited by 87
- 2020Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networkscited by 87
- 2022Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspectivecited by 51
- 2022Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagationcited by 45
- 2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
- 2019Adversarial Feature Training for Generalizable Robotic Visuomotor Controlcited by 7
- 2019Robust Online Model Adaptation by Extended Kalman Filter with Exponential Moving Average and Dynamic Multi-Epoch Strategycited by 6
- 2019Adaptable Human Intention and Trajectory Prediction for Human-Robot Collaborationcited by 4
- 2023Proactive Human-Robot Co-Assembly: Leveraging Human Intention Prediction and Robust Safe Controlcited by 3
Built on by
Citing papers per year: 2025: 2.
2 papers.