Simple Post-Training Robustness Using Test Time Augmentations and Random Forest
This addresses the problem of adversarial robustness for deep learning practitioners by offering a simple, incremental improvement over existing defenses like adversarial training.
The paper tackles the vulnerability of deep neural networks to adversarial attacks by proposing Augmented Random Forest (ARF), a post-training method that uses test time augmentations and a random forest to robustify pretrained models without weight modifications, achieving state-of-the-art adversarial robustness on various attacks with minimal impact on natural image classification.
Although Deep Neural Networks (DNNs) achieve excellent performance on many real-world tasks, they are highly vulnerable to adversarial attacks. A leading defense against such attacks is adversarial training, a technique in which a DNN is trained to be robust to adversarial attacks by introducing adversarial noise to its input. This procedure is effective but must be done during the training phase. In this work, we propose Augmented Random Forest (ARF), a simple and easy-to-use strategy for robustifying an existing pretrained DNN without modifying its weights. For every image, we generate randomized test time augmentations by applying diverse color, blur, noise, and geometric transforms. Then we use the DNN's logits output to train a simple random forest to predict the real class label. Our method achieves state-of-the-art adversarial robustness on a diversity of white and black box attacks with minimal compromise on the natural images' classification. We test ARF also against numerous adaptive white-box attacks and it shows excellent results when combined with adversarial training. Code is available at https://github.com/giladcohen/ARF.