skip to main content

This content will become publicly available on September 1, 2024

Title: Sensitivity of Dynamic Network Slicing to Deep Reinforcement Learning Based Jamming Attacks
In this paper, we consider multi-agent deep reinforcement learning (deep RL) based network slicing agents in a dynamic environment with multiple base stations and multiple users. We develop a deep RL based jammer with limited prior information and limited power budget. The goal of the jammer is to minimize the transmission rates achieved with network slicing and thus degrade the network slicing agents' performance. We design a jammer with both listening and jamming phases and address jamming location optimization as well as jamming channel optimization via deep RL. We evaluate the jammer at the optimized location, generating interference attacks in the optimized set of channels by switching between the jamming phase and listening phase. We show that the proposed jammer can significantly reduce the victims' performance without direct feedback or prior knowledge on the network slicing policies.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
2023 IEEE 34th Annual Inter- national Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Data files were used in support of the research paper titled "“Experimentation Framework for Wireless
    Communication Systems under Jamming Scenarios" which has been submitted to the IET Cyber-Physical Systems: Theory & Applications journal. 

    Authors: Marko Jacovic, Michael J. Liston, Vasil Pano, Geoffrey Mainland, Kapil R. Dandekar


    Top-level directories correspond to the case studies discussed in the paper. Each includes the sub-directories: logs, parsers, rayTracingEmulation, results. 


    logs:    - data logs collected from devices under test
        - 'defenseInfrastucture' contains console output from a WARP 802.11 reference design network. Filename structure follows '*x*dB_*y*.txt' in which *x* is the reactive jamming power level and *y* is the jaming duration in samples (100k samples = 1 ms). 'noJammer.txt' does not include the jammer and is a base-line case. 'outMedian.txt' contains the median statistics for log files collected prior to the inclusion of the calculation in the processing script. 
        - 'uavCommunication' contains MGEN logs at each receiver for cases using omni-directional and RALA antennas with a 10 dB constant jammer and without the jammer. Omni-directional folder contains multiple repeated experiments to provide reliable results during each calculation window. RALA directories use s*N* folders in which *N* represents each antenna state. 
        - 'vehicularTechnologies' contains MGEN logs at the car receiver for different scenarios. 'rxNj_5rep.drc' does not consider jammers present, 'rx33J_5rep.drc' introduces the periodic jammer, in 'rx33jSched_5rep.drc' the device under test uses time scheduling around the periodic jammer, in 'rx33JSchedRandom_5rep.drc' the same modified time schedule is used with a random jammer. 


    parsers:    - scripts used to collect or process the log files used in the study
            - 'defenseInfrastructure' contains the '' script which is used to control and log the throughput of a 5-node WARP 802.11 reference design network. Log files are manually inspected to generate results (end of log file provides a summary). 
            - 'uavCommunication' contains a 'readMe.txt' file which describes the parsing of the MGEN logs using TRPR. TRPR must be installed to run the scripts and directory locations must be updated. 
            - 'vehicularTechnologies' contains the '' script and supporting 'bfb.json' configuration file which also require TRPR to be installed and directories to be updated. 


    rayTracingEmulation:    - 'wirelessInsiteImages': images of model used in Wireless Insite
                - 'channelSummary.pdf': summary of channel statistics from ray-tracing study
                - 'rawScenario': scenario files resulting from code base directly from ray-tracing output based on configuration defined by '*WI.json' file 
                - 'processedScenario': pre-processed scenario file to be used by DYSE channel emulator based on configuration defined by '*DYSE.json' file, applies fixed attenuation measured externally by spectrum analyzer and additional transmit power per node if desired
                - DYSE scenario file format: time stamp (milli seconds), receiver ID, transmitter ID, main path gain (dB), main path phase (radians), main path delay (micro seconds), Doppler shift (Hz), multipath 1 gain (dB), multipath 1 phase (radians), multipath 1 delay relative to main path delay (micro seconds), multipath 2 gain (dB), multipath 2 phase (radians), multipath 2 delay relative to main path delay (micro seconds)
                - 'nodeMapping.txt': mapping of Wireless Insite transceivers to DYSE channel emulator physical connections required
                - 'uavCommunication' directory additionally includes 'antennaPattern' which contains the RALA pattern data for the omni-directional mode ('omni.csv') and directional state ('90.csv')


    results:    - contains performance results used in paper based on parsing of aforementioned log files

    more » « less
  2. Data files were used in support of the research paper titled “Mitigating RF Jamming Attacks at the Physical Layer with Machine Learning" which has been submitted to the IET Communications journal.


    All data was collected using the SDR implementation shown here: Particularly for antenna state selection, the files developed for this paper are located in 'dragonradio/scripts/:'

    • '': class used to defined the antenna state selection algorithm
    • '': SDR implementation for normal radio operation with reconfigurable antenna
    • '': SDR implementation for hyperparameter tunning
    • '': SDR implementation for omnidirectional mode only


    Authors: Marko Jacovic, Xaime Rivas Rey, Geoffrey Mainland, Kapil R. Dandekar


    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)
    • '' is the main parser for training the classifiers
    • 'trainedClassifiers' contains the output classifiers generated by ''

    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
    • '' 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.
    more » « less
  3. In this work, we propose an energy-adaptive moni-toring system for a solar sensor-based smart animal farm (e.g., cattle). The proposed smart farm system aims to maintain high-quality monitoring services by solar sensors with limited and fluctuating energy against a full set of cyberattack behaviors including false data injection, message dropping, or protocol non-compliance. We leverage Subjective Logic (SL) as the belief model to consider different types of uncertainties in opinions about sensed data. We develop two Deep Reinforcement Learning (D RL) schemes leveraging the design concept of uncertainty maximization in SL for DRL agents running on gateways to collect high-quality sensed data with low uncertainty and high freshness. We assess the performance of the proposed energy-adaptive smart farm system in terms of accumulated reward, monitoring error, system overload, and battery maintenance level. We compare the performance of the two DRL schemes developed (i.e., multi-agent deep Q-Iearning, MADQN, and multi-agent proximal policy optimization, MAPPO) with greedy and random baseline schemes in choosing the set of sensed data to be updated to collect high-quality sensed data to achieve resilience against attacks. Our experiments demonstrate that MAPPO with the uncertainty maximization technique outperforms its counterparts. 
    more » « less
  4. Low-resolution analog-to-digital converters (ADCs) simplify the design of millimeter-wave (mmWave) massive multi-user multiple-input multiple-output (MU-MIMO) basestations, but increase vulnerability to jamming attacks. As a remedy, we propose HERMIT (short for Hybrid jammER MITigation), a method that combines a hardware-friendly adaptive analog transform with a corresponding digital equalizer: The analog transform removes most of the jammer’s energy prior to data conversion; the digital equalizer suppresses jammer residues while detecting the legitimate transmit data. We provide theoretical results that establish the optimal analog transform as a function of the user equipments’ and the jammer’s channels. Using simulations with mmWave channel models, we demonstrate the superiority of HERMIT compared both to purely digital jammer mitigation as well as to a recent hybrid method that mitigates jammer interference with a nonadaptive analog transform. 
    more » « less
  5. null (Ed.)
    Robustness of Deep Reinforcement Learning (DRL) algorithms towards adversarial attacks in real world applications such as those deployed in cyber-physical systems (CPS) are of increasing concern. Numerous studies have investigated the mechanisms of attacks on the RL agent's state space. Nonetheless, attacks on the RL agent's action space (corresponding to actuators in engineering systems) are equally perverse, but such attacks are relatively less studied in the ML literature. In this work, we first frame the problem as an optimization problem of minimizing the cumulative reward of an RL agent with decoupled constraints as the budget of attack. We propose the white-box Myopic Action Space (MAS) attack algorithm that distributes the attacks across the action space dimensions. Next, we reformulate the optimization problem above with the same objective function, but with a temporally coupled constraint on the attack budget to take into account the approximated dynamics of the agent. This leads to the white-box Look-ahead Action Space (LAS) attack algorithm that distributes the attacks across the action and temporal dimensions. Our results showed that using the same amount of resources, the LAS attack deteriorates the agent's performance significantly more than the MAS attack. This reveals the possibility that with limited resource, an adversary can utilize the agent's dynamics to malevolently craft attacks that causes the agent to fail. Additionally, we leverage these attack strategies as a possible tool to gain insights on the potential vulnerabilities of DRL agents. 
    more » « less