TRACE:基于拓扑表示的对比学习入侵检测方法
TRACE: Topological Representations for Anomaly detection through Contrastive Embeddings
一篇论文摘要写了三行就讲清短板的难得之作:TRACE 只用良性数据训练入侵检测,在 Unicorn Wget 上 F1 最好,但 GraSec-IoT 反而输给 GraphCL。做安全检测或图学习的开发者可以看看它到底适合哪类数据。
TRACE 是一个面向入侵检测的拓扑感知图对比学习框架,核心思路是只学习良性系统活动图的表示,再用带标签的验证集校准异常阈值,无需攻击标签参与训练。模型将消息传递与拓扑表示结合,在同一投影嵌入空间中为图分配异常分数,从而同时捕捉局部交互和图级结构偏差。
论文在 StreamSpot、GraSec-IoT 和 Unicorn Wget 三个数据集上测试,F1 分数分别为 0.923、0.790 和 0.583。与同样只用良性数据的 GraphCL 基线相比,TRACE 在 StreamSpot 上高出 0.450、在 Unicorn Wget 上高出 0.203,但在 GraSec-IoT 上低于 GraphCL 的 0.975。监督式图神经网络在 StreamSpot 和 GraSec-IoT 上领先,TRACE 仅在 Unicorn Wget 上取得最高 F1。
作者坦承这种混合结果说明:拓扑感知的纯良性学习方法在某些图设置下能提升检测效果,但并非对所有场景都有统一优势。对标签稀缺场景的研究者而言,论文提供了方法的适用边界而非全盘替代方案。
TRACE: Topological Representations for Anomaly detection through Contrastive Embeddings
Intrusion detectors must recognize evolving malicious behavior even when confirmed attack labels are scarce or incomplete. We present TRACE, a topology-aware graph contrastive learning framework for label-efficient intrusion detection. TRACE learns from benign system-activity graphs by combining message-passing and topological representations, then assigns anomaly scores in the same projected embedding space optimized by the contrastive objective. This design captures both local interactions and graph-scale structural deviations without using attack labels during representation learning. A labeled validation set containing benign and malicious graphs is used only to calibrate the anomaly threshold. We evaluate TRACE on StreamSpot, GraSec-IoT, and Unicorn Wget against a supervised graph neural network and the benign-only GraphCL baseline. TRACE obtains F1 scores of 0.923, 0.790, and 0.583, respectively. Compared with GraphCL, this is higher on StreamSpot (0.450) and Unicorn Wget (0.203), but lower on GraSec-IoT (0.975). The supervised model leads on StreamSpot and GraSec-IoT, whereas TRACE has the highest F1 on Unicorn Wget. The mixed results show that topology-aware benign-only learning can improve detection in some graph settings but does not provide a uniform advantage.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. 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 TRACE, intrusion detection, anomaly detection, GraphCL.
Source attribution: curated from arXiv cs.AI (@Sydney Johns).