Shuo Yang (The University of Hong Kong), Xinran Zheng (University College London), Jinze Li (The University of Hong Kong), Jinfeng Xu (The University of Hong Kong), Edith C. H. Ngai (The University of Hong Kong)
Label noise presents a significant challenge in network intrusion detection, leading to erroneous classifications and decreased detection accuracy. Existing methods for handling noisy labels often lack deep insight into network traffic and blindly reconstruct the label distribution to filter samples with noisy labels, resulting in sub-optimal performance. In this paper, we reveal the impact of noisy labels on intrusion detection models from the perspective of causal associations, attributing performance degradation to local consistency of features across categories in network traffic. Motivated by this, we propose CoLD, a textbf{Co}llaborative textbf{L}abel textbf{D}enoising framework for network intrusion detection. CoLD partitions the original feature set into multiple subsets and employs Local Joint Learning to disrupt local consistency, compelling the encoder to learn fine-grained and robust representations. It further applies Causal Collaborative Denoising to detect and filter noisy labels by analyzing causal divergences between multiple representations and their potentially true label, yielding a purified dataset for training a noise-resilient classifier. Experiments on several benchmark datasets demonstrate that CoLD effectively improves classification performance and robustness to label noise, highlighting its potential for enhancing network intrusion detection systems in noisy environments.