NAFN:噪声感知的少样本类增量学习框架应对入侵检测标签噪声
Network Intrusion Detection Adaptability under Spurious Labels: A Noise-Aware Few-Shot Class-Incremental Learning Framework
做安全流量检测的人可以看看这篇:新攻击样本常被标错标签,NAFN 先去噪再用基类统计校准特征重采样,50% 噪声下新类 F1 仍能涨最多 52%,对比普通 FSCIL 基线稳很多,代码也开源了。
论文提出 NAFN,一个面向网络入侵检测系统(NIDS)的噪声感知少样本类增量学习(FSCIL)框架,解决新增攻击类别标注数据易含错误标签的问题。NAFN 包含两个组件:Noise Detection 通过噪声检测算法识别并剔除被误标的 biflow 数据;Feature Sampling 则基于干净的 biflow 估计类条件嵌入,用基类统计量校准后重采样合成特征,恢复原有样本数量。
框架沿用 Rethink Few-Shot(RFS)师生范式,搭配最近邻或逻辑回归等轻量级分类器,并支持多种预训练与记忆选择策略。在 CSE-CIC-IDS2018、Edge-IIoT 和 IoT-NID 三个数据集上的实验显示,即便在 50% 标签噪声下,NAFN 仍能保留旧类知识并保持增量学习性能,新类 F1 分数相比未去噪基线最多提升 52%,同时在跨网络迁移和高噪声场景下保持时间效率。代码已开源以支持复现。
Network Intrusion Detection Adaptability under Spurious Labels: A Noise-Aware Few-Shot Class-Incremental Learning Framework
Network Intrusion Detection Systems (NIDSs) must incrementally adapt to emerging attacks, even when only a limited amount of labeled network traffic is available. Consequently, Few-Shot Class-Incremental Learning (FSCIL)-based NIDSs have gained growing attention. However, existing FSCIL-based NIDSs are highly vulnerable to label noise in newly-observed attack classes. To address this limitation, we propose NAFN, a noise-aware FSCIL-based NIDS framework that reduces the impact of mislabeled data during incremental adaptation. NAFN consists of two components: (i) Noise Detection, which identifies and removes mislabeled biflows using noise-detection algorithms, and (ii) Feature Sampling, which estimates class-conditional embeddings from clean biflows, calibrates them with base-class statistics, and resamples synthetic features to recover the original biflow count. The framework follows the Rethink Few-Shot (RFS) teacher-student paradigm with lightweight nearest-neighbor or logistic regression classifiers, and various pretraining & memory selection strategies. Experiments on CSE-CIC-IDS2018, Edge-IIoT, and IoT-NID datasets show that NAFN effectively preserves prior knowledge and maintains strong incremental performance even under 50% label noise, consistently improving new-class F1-scores over non-denoised baselines, up to +52%, while being time-efficient and robust in cross-network and high-noise incremental settings. The implementation is publicly available to foster reproducibility.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include NAFN, intrusion detection, FSCIL, few-shot learning.
Source attribution: curated from arXiv cs.AI (@Zijian Zhao, Davide Di Monda, Domenico Ciuonzo, Yipeng Wang, Antonio Pescapè).