基于对抗样本的流量特征隐藏方法  

Traffic Feature Obfuscation Method Based on Adversarial Samples

作　　者：李荣 李乐言 Li Rong;Li Leyan(China Electronic Product Reliability and Environmental Testing Research Institute,Guangzhou 510610)

机构地区：[1]中国电子产品可靠性与环境试验研究所,广州510610

出　　处：《信息安全研究》2024年第12期1137-1143,共7页Journal of Information Security Research

基　　金：国家重点研发计划项目(2022YFF0607100)。

摘　　要：深度学习技术的不断发展给智能家居流量隐私保护带来新的挑战,传统的流量隐私保护技术不能有效抵御黑盒场景下的基于深度学习的流量分析攻击.为此,提出了一种基于对抗样本的流量特征隐藏方法,将流量数据转化为图像数据,借助迁移学习构建设备识别模型作为目标对抗模型,并根据流量特征构建生成器网络生成对抗样本.同时,训练网络学习普通流量和对抗样本之间的映射关系并将对抗样本中扰动的位置和大小进行限制,利用模型的迁移性实现黑盒场景中的设备流量隐私保护.实验结果表明,基于对抗样本的流量特征隐藏方法能够有效抵抗未知识别模型的攻击,保护了用户的隐私安全.The continuous development of deep learning poses new challenges for smart home traffic privacy protection.Traditional traffic privacy protection techniques cannot effectively defend against deep learningbased traffic analysis attacks in blackbox scenarios.To address this,this paper investigates a traffic feature obfuscation method based on adversarial samples.It transforms traffic data into image data,leverages transfer learning to build a device recognition model as the target adversarial model,and uses a generator network to construct adversarial samples based on traffic features.Simultaneously,the network is trained to learn the mapping relationship between regular traffic and adversarial samples while restricting the position and size of perturbations in the adversarial samples.This approach utilizes the model’s transferability to achieve device traffic privacy protection in blackbox scenarios.Experimental results demonstrate that the traffic feature obfuscation method based on adversarial samples can effectively resist attacks from unknown recognition models,thereby safeguarding user privacy.

关 键 词：智能家居 隐私保护 深度学习 对抗样本 流量特征隐藏 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]