Data-driven Verification of DNNs for Object Recognition
Not on the map. Why?
Abstract (arXiv)
The paper proposes a new testing approach for Deep Neural Networks (DNN) using gradient-free optimization to find perturbation chains that successfully falsify the tested DNN, going beyond existing grid-based or combinatorial testing. Applying it to an image segmentation task of detecting railway tracks in images, we demonstrate that the approach can successfully identify weaknesses of the tested DNN regarding particular combinations of common perturbations (e.g., rain, fog, blur, noise) on specific clusters of test images.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 20 references that are in the map. First posted on arXiv 17 Jul 2024.
Builds on
12 of 20 references.
References · 12
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
- 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
- 2020Fast is better than free: Revisiting adversarial trainingcited by 727
- 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 251
- 2019Algorithms for Verifying Deep Neural Networkscited by 221
- 2021Data Augmentation Can Improve Robustnesscited by 194
- 2022Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspectivecited by 42
Built on by
Not cited yet.