arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.09818cs.LGcs.NI
收藏

基于监督脉冲神经网络的加密互联网流量分类

Encrypted Internet traffic classification using a supervised Spiking Neural Network

Institut Supérieur de l’Aéronautique et de l’Espace (ISAE-SUPAERO)(高等航空航天学院);University of Toulouse(图卢兹大学);CNRS(法国国家科学研究中心);Université Toulouse 3(图卢兹第三大学);Sharif University of Technology(谢里夫理工大学)

Ali Rasteh, Florian Delpech, Carlos Aguilar-Melchor, Romain Zimmer, Saeed Bagheri Shouraki, Timothée Masquelier

摘要:

互联网流量识别是接入提供商的重要工具,因为识别与网络上传输的不同数据包相关的流量类别有助于他们定义适应的优先级。这意味着,例如,音频会议的高优先级要求和文件传输的低优先级要求,以增强用户体验。随着互联网流量变得越来越加密,主流的经典流量识别技术,有效载荷检查,变得无效。本文使用机器学习技术对加密流量进行分类,只关注数据包大小和到达时间。脉冲神经网络(SNN)主要受到生物神经元运作方式的启发,被用于两个原因。首先,它们能够识别与时间相关的数据包特征。其次,它们可以在具有低能量足迹的神经形态硬件上有效地实现。在这里,我们使用了一个非常简单的前馈SNN,只有一个完全连接的隐藏层,并使用新引入的代理梯度学习方法以监督的方式进行训练。令人惊讶的是,这样一个简单的SNN在ISCX数据集上达到了95.9%的准确率,优于以前的方法。除了更好的准确性外,简单性也有了非常显著的改善:输入大小,神经元数量,可训练参数都减少了一到四个数量级。接下来,我们分析了这种良好准确性的原因。事实证明,除了空间(即数据包大小)特征之外,SNN还利用了时间特征,主要是具有特定大小的数据包的几乎同步(在200 ms范围内)到达时间。总之,这些结果表明,SNN是一个非常适合加密的互联网流量分类:他们可以比传统的人工神经网络(ANN)更准确,他们可以有效地实现低功耗的嵌入式系统。

英文摘要:

Internet traffic recognition is an essential tool for access providers since recognizing traffic categories related to different data packets transmitted on a network help them define adapted priorities. That means, for instance, high priority requirements for an audio conference and low ones for a file transfer, to enhance user experience. As internet traffic becomes increasingly encrypted, the mainstream classic traffic recognition technique, payload inspection, is rendered ineffective. This paper uses machine learning techniques for encrypted traffic classification, looking only at packet size and time of arrival. Spiking neural networks (SNN), largely inspired by how biological neurons operate, were used for two reasons. Firstly, they are able to recognize time-related data packet features. Secondly, they can be implemented efficiently on neuromorphic hardware with a low energy footprint. Here we used a very simple feedforward SNN, with only one fully-connected hidden layer, and trained in a supervised manner using the newly introduced method known as Surrogate Gradient Learning. Surprisingly, such a simple SNN reached an accuracy of 95.9% on ISCX datasets, outperforming previous approaches. Besides better accuracy, there is also a very significant improvement on simplicity: input size, number of neurons, trainable parameters are all reduced by one to four orders of magnitude. Next, we analyzed the reasons for this good accuracy. It turns out that, beyond spatial (i.e. packet size) features, the SNN also exploits temporal ones, mostly the nearly synchronous (within a 200ms range) arrival times of packets with certain sizes. Taken together, these results show that SNNs are an excellent fit for encrypted internet traffic classification: they can be more accurate than conventional artificial neural networks (ANN), and they could be implemented efficiently on low power embedded systems.

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。

↑