Boosting Adversarial Attacks on Neural Networks with Better Optimizer
| Autor: | Jindong Wang, Heng Yin, Ruiyu Dou, Hengwei Zhang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Science (General) Boosting (machine learning) Article Subject Computer Networks and Communications Computer science Iterative method Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Machine learning computer.software_genre Convolutional neural network Q1-390 Robustness (computer science) 020204 information systems 0202 electrical engineering electronic engineering information engineering T1-995 Technology (General) Artificial neural network business.industry Deep learning 020201 artificial intelligence & image processing Artificial intelligence business Gradient descent computer Gradient method Information Systems |
| Zdroj: | Security and Communication Networks, Vol 2021 (2021) |
| DOI: | 10.48550/arxiv.2012.00567 |
| Popis: | Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal images, their existence poses potential security threats to deep learning systems. Sophisticated adversarial examples with strong attack performance can also be used as a tool to evaluate the robustness of a model. However, the success rate of adversarial attacks can be further improved in black-box environments. Therefore, this study combines a modified Adam gradient descent algorithm with the iterative gradient-based attack method. The proposed Adam iterative fast gradient method is then used to improve the transferability of adversarial examples. Extensive experiments on ImageNet showed that the proposed method offers a higher attack success rate than existing iterative methods. By extending our method, we achieved a state-of-the-art attack success rate of 95.0% on defense models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|