Conv-Reluplex: A Verification Framework For Convolution Neural Networks
arXiv:2611.18753 · doi:10.18293/SEKE2021-085
Abstract
In recent years, machine learning has demonstrated impressive performance in many real-world tasks, especially in computer vision and natural language processing. However, to apply them in safety-critical systems one needs formal guarantees on the neural network outputs. The Reluplex tool is proposed to verify the safety of deep neural networks (DNNs), and in case the DNN fails to give a correct output, can generate adversarial examples. Since the tool can only handle DNNs, it is necessary to extend the tool to process image data. Therefore, in this paper, we propose the Conv-Reluplex framework, which is designed to verify the convolutional layer and pooling layer in convolutional neural networks (CNNs), and generate adversarial examples when classification is misguided. We conduct several experiments on MNIST to evaluate our approaches. The results show that the original CNN is improved using the adversarial examples generated by our tool, and the precision of classification can be increased significantly.
arXiv comment6 pages, 8 figures, 5 tables. Published in SEKE 2021
References in corpus (5)
- Explaining and Harnessing Adversarial Examples
- Intriguing properties of neural networks
- Deep Neural Network Compression for Aircraft Collision Avoidance Systems
- Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
- Towards Proving the Adversarial Robustness of Deep Neural Networks