AI 中文总结
针对O-RAN实时异常检测的需求，提出CoMeT-Net框架，通过三项创新实现高准确率、低误报率与低延迟，在测试中表现优于基线方法并通过O-RAN测试床验证。
AI 中文摘要
开放无线接入网（O-RAN）中的实时异常检测要求在资源受限的边缘部署场景下具备高准确率、低误报率和计算效率。传统方法存在计算开销大、跨域性能不一致、特征表示不佳等问题，无法捕捉O-RAN开放接口上的细微攻击。我们提出CoMeT-Net（共识记忆模板网络）这一框架，通过三项创新实现最先进的检测性能：（1）结构化记忆库支持基于模板的共识投票，复杂度为O(N·C)；（2）自适应门控机制将模糊特征作为学习到的噪声滤波器进行降权；（3）对比对齐统一特征学习与分类。CoMeT-Net通过边缘服务器和近实时无线接入网智能控制器（Near-RT RIC）xApp部署在O-RAN基础设施中，可通过物理资源块（PRB）限速和无线资源控制（RRC）连接释放实现动态威胁缓解。在网络流量数据集上，CoMeT-Net的F1分数达99.35%，误报率较基线方法低10倍，同时在从服务器到树莓派4（Raspberry Pi 4）的各硬件层级上保持0.3-3ms的推理延迟。O-RAN测试床验证显示，其能有效隔离攻击，将攻击者延迟降至1400ms以上，同时将合法用户延迟维持在15-20ms。
英文摘要
Real-time anomaly detection in Open Radio Access Networks (O-RAN) demands high accuracy, low false alarms, and computational efficiency for resource-constrained edge deployment. Traditional methods struggle with computational overhead, inconsistent cross-domain performance, and suboptimal feature representations that miss subtle attacks on O-RAN's open interfaces. We present CoMeT-Net (Consensus Memory Template Network), a framework achieving state-of-the-art detection through three innovations: (1) structured memory banks enabling template-based consensus voting with $O(N \cdot C)$ complexity; (2) adaptive gating that downweights ambiguous features as a learned noise filter; (3) contrastive alignment unifying feature learning and classification. Deployed in O-RAN infrastructure via edge servers and Near-RT RIC xApp, CoMeT-Net enables dynamic threat mitigation through PRB throttling and RRC connection release. On network traffic datasets, CoMeT-Net achieves 99.35% F1 score with 10$\times$ lower false alarm rates than baselines while maintaining 0.3-3ms inference across hardware tiers from servers to Raspberry Pi 4. O-RAN testbed validation demonstrates effective isolation, degrading attacker latency to >1400ms while preserving 15-20ms for legitimate users.
CommentsAccepted for publication in the proceedings of the IEEE International Conference on Sensing, Communication, and Networking (SECON), Pisa, Italy, July 2026. Recipient of the Best Student Paper Award
