信息网络安全

信息网络安全 ›› 2026, Vol. 26 ›› Issue (7): 1101-1114.doi: 10.3969/j.issn.1671-1122.2026.07.008

• AI安全防御 • 上一篇    下一篇

基于行为注意力的算力网络异常检测系统

钱晓晟1,2,3, 王利莹1,2,3, 赵宇1,2,3, 刘光亚1,2,3, 王成1,2,3()   

  1. 1 同济大学计算机科学与技术学院， 上海 201804
    2 同济大学嵌入式系统与服务计算教育部重点实验室， 上海 201804
    3 上海人工智能实验室， 上海 200030
  • 收稿日期:2026-01-20 出版日期:2026-07-10 发布日期:2026-09-03
  • 通讯作者: 王成 E-mail:cwang@tongji.edu.cn
  • 作者简介:钱晓晟（1989—），男，江苏，硕士研究生，主要研究方向为算力网络与智能安全|王利莹（1983—），男，上海，高级工程师，博士，主要研究方向为算力网络与智能安全|赵宇（1998—），女，江苏，博士研究生，主要研究方向为算力网络与多智能体系统|刘光亚（1998—），男，湖南，博士研究生，主要研究方向为自然语言处理|王成（1980—），男，山东，教授，博士，CCF会员，主要研究方向为智能安全与网络计算
  • 基金资助:
    国家自然科学基金(59637050);国家自然科学基金(59637051);国家重点研发计划(2023YFD1700202)

Anomaly detection system for computing power networks based on behavioral attention

Qian Xiaosheng1,2,3, Wang Liying1,2,3, Zhao Yu1,2,3, Liu Guangya1,2,3, Wang Cheng1,2,3()   

  1. 1 School of Computer Science and Technology, Tongji University, Shanghai 201804, China
    2 Key Laboratory of Embedded Systems and Service Computing, Ministry of Education, Tongji University, Shanghai 201804, China
    3 Shanghai Artificial Intelligence Laboratory, Shanghai 200030, China
  • Received:2026-01-20 Online:2026-07-10 Published:2026-09-03
  • Contact: Wang Cheng E-mail:cwang@tongji.edu.cn

RichHTML

8

PDF (PC)

19

摘要：

算力网络作为新一代信息基础设施，其高效、稳定运行是保障国家数字经济安全和关键信息基础设施韧性的重要基石。随着算力需求持续增长以及任务规模与复杂度的不断提升，对任务需求进行精准预测，不仅是实现算力资源优化配置的前提，更是识别系统资源异常占用与潜在攻击行为的关键手段。然而，现有方法在处理长序列任务需求时，往往难以捕捉多类型任务中的局部突发波动与复杂动态特征，进而导致资源调度效率下降、异常需求的漏报与误报等问题。为此，文章设计并实现了一个面向算力网络的异常任务需求检测系统。该系统引入行为增强注意力机制，通过结合多尺度统计量与滑动窗口分析，能够动态捕捉任务属性与时序行为特征，从而显著提升对突发模式的识别与预测能力。通过对网络中需求激增行为的精准感知，有助于提前发现潜在的异常流量攻击前兆，为算力资源的安全调度与系统防护提供决策支持。在Alibaba Cluster Traces数据集上的实验结果表明，该系统所集成的行为增强注意力机制在均方误差（MSE）和平均绝对误差（MAE）指标上均取得最优结果，相比现有方法，显著提升了对复杂任务波动的感知精度。综上，该系统不仅提高了算力网络中任务需求预测的准确性与鲁棒性，也增强了对算力网络潜在风险的感知能力。

关键词: 算力网络, 需求预测, 行为增强注意力, 异常检测

Abstract:

As a new-generation information infrastructure, the efficient and stable operation of computing power networks serves as a critical cornerstone for ensuring the security of the national digital economy and the resilience of key information infrastructure. With the continuous growth in computing power demand and the increasing scale and complexity of tasks, accurate prediction of task demands is not only a prerequisite for optimal allocation of computing resources but also a key means of identifying abnormal resource usage and potential attack behaviors. However, existing methods often struggle to capture local sudden fluctuations and complex dynamic patterns across multiple task types when processing long-sequence task demands, leading to reduced resource scheduling efficiency and issues such as missed detections and false alarms for anomalous demands. To address these challenges, this paper designed and implemented an anomalous task demand detection system for computing power networks. The system introduced a behavior-enhanced attention mechanism that, by integrating multi-scale statistical measures with sliding window analysis, dynamically captures task attributes and temporal behavioral features, thereby significantly improving the identification and prediction of sudden patterns. Through precise sensing of demand surge behaviors in the network, the system helped detect potential precursors of anomalous traffic attacks in advance, providing decision support for secure scheduling of computing resources and system protection. Experimental results on the Alibaba Cluster Traces dataset demonstrate that the behavior-enhanced attention mechanism integrated into the system achieves optimal performance in terms of both mean squared error (MSE) and mean absolute error (MAE), significantly outperforming existing methods in perception accuracy for complex task fluctuations. In summary, the proposed system not only improves the accuracy and robustness of task demand prediction in computing power networks but also enhances the perception of potential risks.

Key words: computing power networks, demand forecast, behavior enhanced attention, anomaly detection

中图分类号: