Self-Supervised Representation Learning for Adversarial Attack Detection
This addresses the issue of domain shift in adversarial attack detection for computer vision applications, though it appears incremental as it builds on existing self-supervised and contrastive learning techniques.
The paper tackles the problem of adversarial attack detection by proposing a self-supervised representation learning framework to reduce reliance on labeled data and improve cross-domain performance, achieving state-of-the-art results across a wide range of images.
Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised representation learning framework for the adversarial attack detection task to address this drawback. Firstly, we map the pixels of augmented input images into an embedding space. Then, we employ the prototype-wise contrastive estimation loss to cluster prototypes as latent variables. Additionally, drawing inspiration from the concept of memory banks, we introduce a discrimination bank to distinguish and learn representations for each individual instance that shares the same or a similar prototype, establishing a connection between instances and their associated prototypes. We propose a parallel axial-attention (PAA)-based encoder to facilitate the training process by parallel training over height- and width-axis of attention maps. Experimental results show that, compared to various benchmark self-supervised vision learning models and supervised adversarial attack detection methods, the proposed model achieves state-of-the-art performance on the adversarial attack detection task across a wide range of images.