Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks
This addresses the challenge of adversarial robustness in CNNs for applications requiring efficient and secure image classification, representing an incremental improvement by reducing complexity while maintaining defense.
The paper tackles the problem of making CNNs robust against adversarial attacks without increasing computational complexity, proposing the Code-Bridged Classifier (CBC) framework that uses a stacked encoder-convolutional model to achieve both improved robustness and lower computational overhead compared to prior defenses.
In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even by decreasing the overall models' computational complexity. More specifically, we propose a stacked encoder-convolutional model, in which the input image is first encoded by the encoder module of a denoising auto-encoder, and then the resulting latent representation (without being decoded) is fed to a reduced complexity CNN for image classification. We illustrate that this network not only is more robust to adversarial examples but also has a significantly lower computational complexity when compared to the prior art defenses.