arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.07510cs.AIcs.CR
收藏

一种基于时间频谱的攻击流量识别方法

An Attack Traffic Identification Method Based on Temporal Spectrum

Trend Micro Nanjing Branch(趋势科技南京分公司);Jiangsu Police Institute (JSPI)(江苏警官学院);University of California, Los Angeles (UCLA)(加州大学洛杉矶分校)

Wenwei Xie, Jie Yin, Zihao Chen

AI总结:

针对网络攻击检测中鲁棒性不足、特征不稳定及噪声干扰问题,提出基于时间频谱的检测识别方法,利用滑动窗口构建序列并结合SSPE与COAP方法生成频谱标签与时间特征,使模型识别准确率提升10%且在噪声下鲁棒性强。

摘要:

为了解决现有网络攻击检测与识别模型中鲁棒性不足、特征不稳定以及数据噪声干扰的问题,本文提出了一种基于时间频谱的攻击流量检测与识别方法。首先,通过滑动窗口对流量数据进行分段,构建网络流量的特征序列及相应的标签序列。接着,应用所提出的频谱标签生成方法 SSPE 和 COAP,将标签序列转换为频谱标签,将特征序列转换为时间特征。频谱标签和时间特征被用于捕获和表示攻击的行为模式。最后,利用构建的时间特征和频谱标签训练模型,进而检测并识别网络攻击行为。实验结果表明,与传统方法相比,使用 SSPE 或 COAP 方法训练的模型将识别准确率提高了 10%,并表现出极强的鲁棒性,尤其是在噪声环境中。

英文摘要:

To address the issues of insufficient robustness, unstable features, and data noise interference in existing network attack detection and identification models, this paper proposes an attack traffic detection and identification method based on temporal spectrum. First, traffic data is segmented by a sliding window to construct a feature sequence and a corresponding label sequence for network traffic. Next, the proposed spectral label generation methods, SSPE and COAP, are applied to transform the label sequence into spectral labels and the feature sequence into temporal features. Spectral labels and temporal features are used to capture and represent behavioral patterns of attacks. Finally, the constructed temporal features and spectral labels are used to train models, which subsequently detects and identifies network attack behaviors. Experimental results demonstrate that compared to traditional methods, models trained with the SSPE or COAP method improve identification accuracy by 10%, and exhibit strong robustness, particularly in noisy environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑