返回
An adversarial defense algorithm based on robust U-net
DOI:10.1007/s11042-023-17355-w.png)
摘要
En 中文
Due to the continuous development of neural network technology, it has been widely applied in fields such as autonomous driving and biomedicine. However, adversarial attacks can significantly degrade the performance and reliability of neural networks, making defending against such attacks a crucial research area. In this paper, we propose a robust U-Net and adversarial generative network-based defense method, training the target model on a clean training set without adversarial samples. Firstly, we train the target neural network on a clean training set. Then, we train the robust U-Net using the clean training set, employing reparameterization and random noise to resist adversarial perturbations. To supervise the quality of transformed images, we employ the adversarial generative network, utilizing the RU-Net as the generator and a discriminator to ensure the quality of generated images. Finally, we use the transformed images to retrain the target neural network, obtaining a robust neural network model capable of defending against adversarial attacks. Experimental evaluations on CIFAR-10 and Tiny Image Net demonstrate the effectiveness of our method in countering adversarial attacks and enhancing neural network robustness.
Keyword:
Neural networks
Vulnerability
Robust U-net
Adversarial generative network
Adversarial robustness
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
Sensorless Control of Z Source Inverter fed BLDC Motor Drive by FOC - DTC Hybrid Control Strategy Using Fuzzy Logic Controller采用模糊逻辑控制器的foc-dtc混合控制策略的Z源逆变器馈电BLDC电机驱动的无传感器控制
Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
Enhanced Reactivity of Dinuclear Copper(I) Acetylides in Dipolar Cycloadditions偶极环加成反应中双核乙炔铜 (I) 的反应性增强

