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

arXiv: https://arxiv.org/abs/2205.09669 · HTML: https://mlsanity.com/paper/2205.09669/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 56 references that are in the map.
- First posted on arXiv 19 May 2022.

## Builds on (most cited first, 16 of 16)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [S4L: Self-Supervised Semi-Supervised Learning](https://mlsanity.com/paper/1905.03670/) (2019)
- [Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2103.00113/) (2021)
- [Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection](https://mlsanity.com/paper/1802.09089/) (2018)
- [Semi-supervised Semantic Segmentation with Directional Context-aware Consistency](https://mlsanity.com/paper/2106.14133/) (2021)
- [Poisoning the Unlabeled Dataset of Semi-Supervised Learning](https://mlsanity.com/paper/2105.01622/) (2021)
- [Evaluating and Improving Adversarial Robustness of Machine Learning-Based Network Intrusion Detectors](https://mlsanity.com/paper/2005.07519/) (2020)
- [New Directions in Automated Traffic Analysis](https://mlsanity.com/paper/2008.02695/) (2020)
- [Realtime Robust Malicious Traffic Detection via Frequency Domain Analysis](https://mlsanity.com/paper/2106.14707/) (2021)
- [Random Partitioning Forest for Point-Wise and Collective Anomaly Detection -- Application to Intrusion Detection](https://mlsanity.com/paper/2006.16801/) (2020)
- [Long-tailed Distribution Adaptation](https://mlsanity.com/paper/2110.02686/) (2021)
- [Walling up Backdoors in Intrusion Detection Systems](https://mlsanity.com/paper/1909.07866/) (2019)

## Built on by (most cited first, 6 of 6)

- [LViT: Language meets Vision Transformer in Medical Image Segmentation](https://mlsanity.com/paper/2206.14718/) (2022)
- [ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation](https://mlsanity.com/paper/2402.02029/) (2024)
- [Coarse-to-Fine Covid-19 Segmentation via Vision-Language Alignment](https://mlsanity.com/paper/2303.00279/) (2023)
- [A Comprehensive Survey on the Security of Smart Grid: Challenges, Mitigations, and Future Research Opportunities](https://mlsanity.com/paper/2407.07966/) (2024)
- [Optimizing Universal Lesion Segmentation: State Space Model-Guided Hierarchical Networks with Feature Importance Adjustment](https://mlsanity.com/paper/2404.17235/) (2024)
- [OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis](https://mlsanity.com/paper/2607.25108/) (2026)

## Abstract (arXiv)

Supervised learning has been widely used for attack categorization, requiring high-quality data and labels. However, the data is often imbalanced and it is difficult to obtain sufficient annotations. Moreover, supervised models are subject to real-world deployment issues, such as defending against unseen artificial attacks. To tackle the challenges, we propose a semi-supervised fine-grained attack categorization framework consisting of an encoder and a two-branch structure and this framework can be generalized to different supervised models. The multilayer perceptron with residual connection 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 data imbalance problem, 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 propose an Active Adaption Resampling (AAR) method, which can better discover the distribution of unseen sample data and adapt the parameters of encoder. Experimental results show that our model outperforms the state-of-the-art semi-supervised attack detection methods with a 3% improvement in classification accuracy and a 90% reduction in training time.