D2R: dual regularization loss with collaborative adversarial generation for model robustness
This work addresses adversarial attacks for deep learning models, presenting an incremental improvement over existing collaborative learning frameworks.
The paper tackled the problem of insufficient guidance and non-collaborative adversarial generation in deep neural network robustness by proposing a dual regularization loss and collaborative adversarial generation strategy, resulting in highly robust models as demonstrated on benchmark datasets like CIFAR-10, CIFAR-100, and Tiny ImageNet.
The robustness of Deep Neural Network models is crucial for defending models against adversarial attacks. Recent defense methods have employed collaborative learning frameworks to enhance model robustness. Two key limitations of existing methods are (i) insufficient guidance of the target model via loss functions and (ii) non-collaborative adversarial generation. We, therefore, propose a dual regularization loss (D2R Loss) method and a collaborative adversarial generation (CAG) strategy for adversarial training. D2R loss includes two optimization steps. The adversarial distribution and clean distribution optimizations enhance the target model's robustness by leveraging the strengths of different loss functions obtained via a suitable function space exploration to focus more precisely on the target model's distribution. CAG generates adversarial samples using a gradient-based collaboration between guidance and target models. We conducted extensive experiments on three benchmark databases, including CIFAR-10, CIFAR-100, Tiny ImageNet, and two popular target models, WideResNet34-10 and PreActResNet18. Our results show that D2R loss with CAG produces highly robust models.