Mitigating RF Jamming Attacks at the Physical Layer with Machine Learning Dataset
收藏资源简介：
Data files were used in support of the research paper titled “<em>Mitigating RF Jamming Attacks at the Physical Layer with Machine Learning</em>" which has been submitted to the IET Communications journal. --------------------------------------------------------------------------------------------- All data was collected using the SDR implementation shown here: https://github.com/mainland/dragonradio/tree/iet-paper. Particularly for antenna state selection, the files developed for this paper are located in 'dragonradio/scripts/:' 'ModeSelect.py': class used to defined the antenna state selection algorithm 'standalone-radio.py': SDR implementation for normal radio operation with reconfigurable antenna 'standalone-radio-tuning.py': SDR implementation for hyperparameter tunning 'standalone-radio-onmi.py': SDR implementation for omnidirectional mode only --------------------------------------------------------------------------------------------- Authors: Marko Jacovic, Xaime Rivas Rey, Geoffrey Mainland, Kapil R. Dandekar<br> Contact: krd26@drexel.edu --------------------------------------------------------------------------------------------- Top-level directories and content will be described below. Detailed descriptions of experiments performed are provided in the paper. --------------------------------------------------------------------------------------------- classifier_training: files used for training classifiers that are integrated into SDR platform 'logs-8-18' directory contains OTA SDR collected log files for each jammer type and under normal operation (including congested and weaklink states) 'classTrain.py' is the main parser for training the classifiers 'trainedClassifiers' contains the output classifiers generated by 'classTrain.py' post_processing_classifier: contains logs of online classifier outputs and processing script 'class' directory contains .csv logs of each RTE and OTA experiment for each jamming and operation scenario 'classProcess.py' parses the log files and provides classification report and confusion matrix for each multi-class and binary classifiers for each observed scenario - found in 'results->classifier_performance' post_processing_mgen: contains MGEN receiver logs and parser 'configs' contains JSON files to be used with parser for each experiment 'mgenLogs' contains MGEN receiver logs for each OTA and RTE experiment described. Within each experiment logs are separated by 'mit' for mitigation used, 'nj' for no jammer, and 'noMit' for no mitigation technique used. File names take the form *_cj_* for constant jammer, *_pj_* for periodic jammer, *_rj_* for reactive jammer, and *_nj_* for no jammer. Performance figures are found in 'results->mitigation_performance' ray_tracing_emulation: contains files related to Drexel area, Art Museum, and UAV Drexel area validation RTE studies. Directory contains detailed 'readme.txt' for understanding. Please note: the processing files and data logs present in 'validation' folder were developed by Wolfe et al. and should be cited as such, unless explicitly stated differently. S. Wolfe, S. Begashaw, Y. Liu and K. R. Dandekar, "Adaptive Link Optimization for 802.11 UAV Uplink Using a Reconfigurable Antenna," MILCOM 2018 - 2018 IEEE Military Communications Conference (MILCOM), 2018, pp. 1-6, doi: 10.1109/MILCOM.2018.8599696. results: contains results obtained from study 'classifier_performance' contains .txt files summarizing binary and multi-class performance of online SDR system. Files obtained using 'post_processing_classifier.' 'mitigation_performance' contains figures generated by 'post_processing_mgen.' 'validation' contains RTE and OTA performance comparison obtained by 'ray_tracing_emulation->validation->matlab->outdoor_hover_plots.m' tuning_parameter_study: contains the OTA log files for antenna state selection hyperparameter study 'dataCollect' contains a folder for each jammer considered in the study, and inside each folder there is a CSV file corresponding to a different configuration of the learning parameters of the reconfigurable antenna. The configuration selected was the one that performed the best across all these experiments and is described in the paper. 'data_summary.txt'this file contains the summaries from all the CSV files for convenience.
本数据集用于支持已提交至IET Communications期刊的研究论文《利用机器学习缓解物理层射频（Radio Frequency, RF）干扰攻击》（Mitigating RF Jamming Attacks at the Physical Layer with Machine Learning）。 --------------------------------------------------------------------------------------------- 所有数据均通过此处展示的软件定义无线电（Software Defined Radio, SDR）实现方案采集，具体地址为：https://github.com/mainland/dragonradio/tree/iet-paper。针对天线状态选择任务，为本论文开发的相关文件位于`dragonradio/scripts/`目录下： - `ModeSelect.py`：用于定义天线状态选择算法的类 - `standalone-radio.py`：支持可重构天线的常规无线电运行的SDR实现方案 - `standalone-radio-tuning.py`：用于超参数调优的SDR实现方案 - `standalone-radio-onmi.py`：仅支持全向模式的SDR实现方案 --------------------------------------------------------------------------------------------- 作者：Marko Jacovic、Xaime Rivas Rey、Geoffrey Mainland、Kapil R. Dandekar 联系方式：krd26@drexel.edu --------------------------------------------------------------------------------------------- 下文将对顶层目录及内容进行说明，具体实验的详细描述请参见发表论文。 1. `classifier_training`：用于训练集成至SDR平台的分类器的相关文件。 - `logs-8-18` 目录包含针对每种干扰类型及正常运行（含拥塞与弱链路状态）场景采集的空口（Over-the-Air, OTA）SDR日志文件。 - `classTrain.py` 是训练分类器的主解析脚本。 - `trainedClassifiers` 存放由`classTrain.py`生成的已训练分类器。 2. `post_processing_classifier`：包含在线分类器输出日志与处理脚本。 - `class` 目录包含针对每种干扰与运行场景的实时实验（Real-Time Experiment, RTE）与空口实验的CSV格式日志文件。 - `classProcess.py` 用于解析日志文件，并为每种观测场景下的多分类与二分类器生成分类报告与混淆矩阵，结果存放于`results->classifier_performance`目录。 3. `post_processing_mgen`：包含MGEN接收机日志与解析脚本。 - `configs` 目录包含适用于各实验解析的JSON配置文件。 - `mgenLogs` 目录包含本文所述所有空口与实时实验的MGEN接收机日志。各实验日志按如下方式分类：`mit` 表示启用缓解机制，`nj` 表示无干扰，`noMit` 表示未使用缓解技术。文件名格式为：`*_cj_*` 代表恒定干扰机，`*_pj_*` 代表周期性干扰机，`*_rj_*` 代表响应式干扰机，`*_nj_*` 代表无干扰场景。性能图表存放于`results->mitigation_performance`目录。 4. `ray_tracing_emulation`：包含与德雷塞尔大学区域、艺术博物馆及无人机实时实验验证相关的文件。本目录包含详细的`readme.txt`以供理解。请注意：`validation` 文件夹中的处理脚本与数据日志由Wolfe等人开发，除非另有说明，需按如下文献引用：S. Wolfe, S. Begashaw, Y. Liu and K. R. Dandekar, "Adaptive Link Optimization for 802.11 UAV Uplink Using a Reconfigurable Antenna," MILCOM 2018 - 2018 IEEE Military Communications Conference (MILCOM), 2018, pp. 1-6, doi: 10.1109/MILCOM.2018.8599696. 5. `results`：包含本研究获得的所有结果。 - `classifier_performance` 目录包含总结在线SDR系统二分类与多分类性能的TXT文件，由`post_processing_classifier`生成。 - `mitigation_performance` 目录包含由`post_processing_mgen`生成的性能图表。 - `validation` 目录包含由`ray_tracing_emulation->validation->matlab->outdoor_hover_plots.m`生成的实时实验与空口实验性能对比结果。 6. `tuning_parameter_study`：包含天线状态选择超参数研究的空口日志文件。 - `dataCollect` 目录包含针对本研究中每种干扰类型的文件夹，每个文件夹内包含对应可重构天线学习参数不同配置的CSV文件。本研究选取了在所有实验中表现最优的配置，具体描述参见论文。 - `data_summary.txt` 为方便查阅，包含所有CSV文件的汇总信息。
