Semi-WTC: A Practical Semi-supervised Framework for Attack Categorization through Weight-Task Consistency

Abstract

Supervised learning has been widely used for attack detection, which requires large amounts of high-quality data and labels. However, the data is often imbalanced and sufficient annotations are difficult to obtain. Moreover, these supervised models are subject to real-world deployment issues, such as defending against unseen artificial attacks. We propose a semi-supervised fine-grained attack categorization framework consisting of an encoder and a two-branch structure to integrate information from labeled and unlabeled data to tackle these practical challenges. This framework can be generalized to different supervised models. The multilayer perceptron with residual connection and batch normalization is used as the encoder to extract features and reduce the complexity. The Recurrent Prototype Module (RPM) is proposed to train the encoder effectively in a semi-supervised manner. To alleviate the problem of data imbalance, we introduce the Weight-Task Consistency (WTC) into the iterative process of RPM by assigning larger weights to classes with fewer samples in the loss function. In addition, to cope with new attacks in real-world deployment, we further propose an Active Adaption Resampling (AAR) method, which can better discover the distribution of the unseen sample data and adapt the parameters of the encoder. Experimental results show that our model outperforms the state-of-the-art semi-supervised attack detection methods with a general 5% improvement in classification accuracy and a 90% reduction in training time.

ScribFormer: Transformer Makes CNN Work Better for Scribble-Based Medical Image Segmentation

“…To address the second issue of expanding scribble annotations for WSSS, class activation maps (CAMs) [17], [18] are often used to generate initial seeds for localization. However, the pseudo labels generated from CAMs for training a WSSS model have an issue of partial activation, which generally tends to highlight the most discriminative part of an object instead of the entire object area [19], [20].…”