| 摘要: |
| 信息设备会在工作过程中无意进行电磁辐射，通过特定手段可以对电磁辐射信号进行截获并还原，获取信息设备处理的敏感信息，威胁到国家及个人的信息安全。此外，这些电磁辐射信号也会泄漏计算机的硬件信息，这对部分攻击者、防护者和安全检查人员更为关键。通过识别电磁辐射信号，找到电磁辐射发射源，有针对性地进行信息安全防护具有重要意义。本文通过研究不同计算机设备电磁辐射信号的特点，借鉴说话人识别研究中的特征提取方法，并引入深度学习技术，提出一种新的计算机个体识别方法。该方法基于短时能量(Short Time Energy, STE)和线性预测分析(Linear Prediction Coefficient, LPC)两种信号分析方式，进行数据预处理，在完成数据降维工作的同时，提取浅层数据特征，并采用卷积神经网络(Convolutional Neural Network, CNN)进行计算机个体识别。卷积神经网络将特征提取和分类器有效结合到一个框架中，从样本中学习数据的本质特征，实现复杂函数的逼近，本文主要使用卷积神经网络完成自动深度特征提取和分类识别工作，将提取信号特征和分类两个原本割裂的工作结合，简化人工提取特征的操作，有效提升计算机个体识别的可拓展性和环境适应性。经实验验证，本文提出的模型在我们的实验环境中识别准确率可达97.8%，具有较好的计算机个体识别能力。同时，本文通过实验仿真对该算法在不同信噪比条件下的性能进行了评价，验证了该方法的鲁棒性。 |
| 关键词: 电磁辐射 信号处理 深度学习 个体识别 电磁信息安全 |
| DOI：10.19363/J.cnki.cn10-1380/tn.2024.04.03 |
| 投稿时间：2022-01-21修订日期：2022-03-29 |
| 基金项目:中国科学院战略性先导科技专项 |
|
| Computer Recognition Based on Convolutional Neural Network |
|
ZHENG Xueqi, XU Yanyun, HUANG Weiqing
|
| (The 4th Laboratory,Institute of Information Engineering,Chinese Academy of Sciences) |
| Abstract: |
| Information equipment will inadvertently emit electromagnetic radiation during work, and electromagnetic radiation signals can be intercepted and restored to obtain sensitive information processed by the information equipment, posing a threat to national and personal information security. In addition, the radiation may reveal the hardware information of the computer, which is more important for some attackers, protectors and security inspection workers. It is critical to detect the electromagnetic leakage signal, track down the source of the leakage, and implement targeted information security protection. The purpose of this research is to present a new method of computer individual identification based on an examination of the characteristics of electromagnetic leakage signals from various computer equipment. Drawing on feature extraction methods in speaker recognition research and introducing deep learning technology, this method, which is based on Short Time Energy (STE) and Linear Prediction Coefficient (LPC), Extract shallow features of electromagnetic leakage signals. Then use Convolutional Neural Network (CNN) to identify the computers individually Convolutional neural network effectively combines feature extraction and classifier into one framework, learns the essential characteristics of data from samples, and realizes the approximation of complex functions. This paper mainly uses convolutional neural network to complete automatic deep feature extraction and classification and recognition. The extraction of signal features and the classification of two originally separated tasks are combined to simplify the operation of manual feature extraction and effectively improve the scalability and environmental adaptability of computer individual recognition. Experimental validation shows that in our experiment environment the model provided in this paper has a recognition accuracy of 97.8 percent on the verification set, which shows that our model has good computer individual recognition capabilities and can identify computers accurately through electromagnetic radiation. At the same time, we evaluates the performance of the model under different signal-to-noise ratio conditions through experimental simulation, which verifies the robustness of the method. |
| Key words: compromising emanations signal processing deep leaning individual identification electromagnetic information security |
