ST-GAT:防泄漏的时空图注意力网络用于入侵检测
ST-GAT: A Leakage-Free Spatio-Temporal Graph Attention Framework for Robust Network Intrusion Detection
做网络安全或流量检测的值得看看。作者指出 CSE-CIC-IDS-2018 这类基准的分数普遍被时间泄漏和预处理污染虚高,他们的 ST-GAT 用非重叠窗口加图注意力,Macro-F1 比 Random Forest 高 14.3 个百分点,方法论部分可以直接套用到自己的评估流程里。
一篇 arXiv 论文提出 ST-GAT(Spatio-Temporal Graph Attention Network),用图快照序列建模网络流量做入侵检测。
方法在每个时间窗口内用 k-NN 建边,接多头 GAT 做空间聚合,再用 BiLSTM 加时间注意力做序列建模。针对标准基准 CSE-CIC-IDS-2018 上常见的两类评估失真——滑动窗口重叠造成的时间泄漏、预处理在训练/测试划分前拟合造成的污染——论文采用步长等于窗口长度的非重叠窗口,并只在训练集上拟合预处理。
在三个随机种子下,使用逆类频率加权的 ST-GAT 取得 Macro-F1 96.65%(±0.
87)、准确率 99.14%,比逐流的 Random Forest 基线(82.
34%)的 Macro-F1 高 14.3 个百分点。
论文还比较了三种类不平衡策略:动态均衡采样使 Macro-F1 降至 94.37%,比损失加权低 2.
3 个百分点,说明对噪声多的少数类做激进重采样可能损害检测效果。
ST-GAT: A Leakage-Free Spatio-Temporal Graph Attention Framework for Robust Network Intrusion Detection
Intrusion detection systems are a central defence in modern networks. Deep learning models report strong anomaly-detection results, but evaluations on standard benchmarks such as CSE-CIC-IDS-2018 are often inflated by two methodological problems: temporal leakage from overlapping sliding windows, and contamination from preprocessing fitted before the train/test split. Per-flow classifiers also ignore the spatio-temporal dependencies across sequences of network flows. We propose a Spatio-Temporal Graph Attention Network (ST-GAT) that represents traffic as a sequence of graph snapshots. It builds k-Nearest Neighbour (k-NN) edges within each window, applies multi-head Graph Attention Network (GAT) layers for spatial aggregation, and uses a Bidirectional Long Short-Term Memory (BiLSTM) network with temporal attention for sequence modelling. To prevent leakage, we use non-overlapping temporal windows (stride equal to window length) and fit all preprocessing on the training split only. We compare three class-imbalance strategies: inverse class-frequency weighting, dynamic balanced sampling, and few-shot metric prototyping. Across three random seeds, ST-GAT with inverse class weighting reached a Macro-F1 of 96.65% (+/- 0.87) and an accuracy of 99.14%. This is 14.3 percentage points higher in Macro-F1 than a per-flow Random Forest baseline (82.34%). Balanced sampling reduced Macro-F1 by 2.3 points (to 94.37%) relative to loss weighting. This suggests that aggressive resampling of small, noisy minority classes can hurt detection in heavily imbalanced traffic.
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 ST-GAT, intrusion detection, BiLSTM, CSE-CIC-IDS-2018.
Source attribution: curated from arXiv cs.LG (@Nikhil Parkar, Sanskar Pandey, Siddhi Prajapati, Suganeshwari G, Syed Ibrahim).