| 引用本文: | 相迎宵,李轶珂,刘吉强,王潇瑾,陈彤,童恩栋,牛温佳,韩臻.面向降频污染攻击的智能交通拥堵态势量化分析.软件学报,2023,34(2):833-848 |
| |
|
| 本文已被：浏览 1553次 下载 3388次 |
码上扫一扫！ |
|
|
| 面向降频污染攻击的智能交通拥堵态势量化分析 |
|
相迎宵1,2, 李轶珂1,2, 刘吉强1,2, 王潇瑾1,2, 陈彤1,2, 童恩栋1,2, 牛温佳1,2, 韩臻1,2
|
|
1.智能交通数据安全与隐私保护技术北京市重点实验室, 北京 100044;2.北京交通大学, 北京 100044
|
|
| 摘要: |
| 随着网联车辆的快速发展和开放化，智能信号灯规划系统承受着巨大的网络攻击风险.已有相关研究发现，定频数据污染对规划脆弱性的攻击造成了交通拥堵爆增，但缺乏对降频污染攻击的全时序拥堵态势量化与分析，在检测预警与持续对抗方面有一定的局限性.将开源智能信号灯规划系统I-SIG及其规划算法COP作为研究对象，提出一种面向多个降频污染攻击的统一拥堵态势量化与分析框架，构造态势发展的时空序列三阶张量空间，并设计极值分析、平稳性分析和关联性分析，实现基于函数依赖关系的一体化分析方法.在交通模拟环境VISSIM平台上，验证了该量化分析的有效性并报告新发现. |
| 关键词: 污染攻击 拥堵态势 量化分析 智能交通 张量空间 |
| DOI：10.13328/j.cnki.jos.006416 |
| 分类号:TP309 |
| 基金项目:中央高校基本科研业务费专项资金（2021JBM006）；国家自然科学基金（61972025，61802389，61672092，U1811264，61966009）；国家重点研发计划（2020YFB1005604，2020YFB2103802） |
|
| Quantified Analysis of Congestion Situation in Intelligent Transportation Towards Frequency-reduced Spoofing Attack |
|
XIANG Ying-Xiao1,2, LI Yi-Ke1,2, LIU Ji-Qiang1,2, WANG Xiao-Jin1,2, CHEN Tong1,2, TONG En-Dong1,2, NIU Wen-Jia1,2, HAN Zhen1,2
|
|
1.Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing 100044, China;2.Beijing Jiaotong University, Beijing 100044, China
|
| Abstract: |
| With the development and openness of connected vehicle, the planning system of intelligent signal system (I-SIG system) has a big security threat from network attack. Former work has revealed that a frequency-fixed data spoofing attack to the planning weakness can cause a heavy traffic congestion. However, there is still very limited knowledge for security detection, warning, and defense, and there is no work that provides a full time-serial congestion situation quantification and analysis for various attack frequency from high to low. Targeting the open source I-SIG system and its COP planning algorithm, this study proposes a unified framework to quantify and analyze the congestion situation under multiple spoofing attack from high to low frequency. Firstly, a space-time tensor space of three ordersis constructed. Based on tensor computation, a function-dependent integrated analysis approach is implemented, in which the max-min analysis, stationarity analysis, and correlation analysis are developed. Experiments on the traffic simulation platform VISSIM show the effectiveness of quantification and analysis, and demonstrate that the results are meaningful. |
| Key words: spoofing attack congestion situation quantified analysis intelligent transportation tensor space |
