Certifying Global Robustness for Deep Neural Networks
Not on the map. Why?
Abstract (arXiv)
A globally robust deep neural network resists perturbations on all meaningful inputs. Current robustness certification methods emphasize local robustness, struggling to scale and generalize. This paper presents a systematic and efficient method to evaluate and verify global robustness for deep neural networks, leveraging the PAC verification framework for solid guarantees on verification results. We utilize probabilistic programs to characterize meaningful input regions, setting a realistic standard for global robustness. Additionally, we introduce the cumulative robustness curve as a criterion in evaluating global robustness. We design a statistical method that combines multi-level splitting and regression analysis for the estimation, significantly reducing the execution time. Experimental results demonstrate the efficiency and effectiveness of our verification method and its capability to find rare and diversified counterexamples for adversarial training.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 31 May 2024.
Builds on
29 of 44 references.
References · 29
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
- 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
- 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
- 2018Certified Defenses against Adversarial Examplescited by 305
- 2016Safety Verification of Deep Neural Networkscited by 262
- 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
- 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
- 2019Algorithms for Verifying Deep Neural Networkscited by 221
17 more
- 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 178
- 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
- 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
- 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 123
- 2021Globally-Robust Neural Networkscited by 106
- 2019Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programmingcited by 100
- 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
- 2016Measuring Neural Net Robustness with Constraintscited by 90
- 2017Output Reachable Set Estimation and Verification for Multi-Layer Neural Networkscited by 79
- 2019Quantitative Verification of Neural Networks And its Security Applicationscited by 56
- 2018A Statistical Approach to Assessing Neural Network Robustnesscited by 54
- 2018CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networkscited by 50
- 2019Robustness of Neural Networks: A Probabilistic and Practical Approachcited by 38
- 2018Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distributioncited by 32
- 2020Learning Task-General Representations with Generative Neuro-Symbolic Modelingcited by 14
- 2020Certifying Neural Network Robustness to Random Input Noise from Samplescited by 4
- 2019Decoder Choice Network for Meta-Learningcited by 3
Built on by
Not cited yet.