Neutralizing a drone using a protocol-aware RF jammer requires precise knowledge of the occupied spectrum in the time and frequency domains. This paper aims to develop an automatic spectrum prediction framework utilizing the Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) models. We generate a synthetic dataset using the commonly used drone signal properties and parameters, and evaluate the prediction performance under several realistic scenarios. Our experiment shows that the CNN-LSTM model can accurately predict future time and frequency sequences by using the spectrogram matrix as the input. We obtained better prediction performance with lower computational costs with our framework compared to the existing frameworks. Furthermore, we show that the CNN-LSTM model can predict future timefrequency sequences of unseen hopping rates and patterns when using transfer learning. The performance validation is also performed using real drone RF signals. Furthermore, we present a two-stage spectrum prediction approach that achieves excellent performance by offering higher frequency resolutions while maintaining a lower computational cost.

In this paper a summary is given of the ongoing research at the Belgian Royal Military Academy in the field of mobile ad hoc networks in general and wireless sensor networks (WSNs) in particular. In this study, all wireless sensor networks are based on the physical and the medium access layer of the IEEE 802.15.4 low rate wireless personal area networks standard. The paper gives a short overview of the IEEE 802.15.4 standard in the beaconless mode together with a description of the sensor nodes and the software used throughout this work. The paper also reports on the development of a packet sniffer for IEEE 802.15.4 integrated in wireshark. This packet sniffer turns out to be indispensable for debugging purposes. In view of future applications on the wireless network, we made a theoretical study of the effective data capacity and compared this with measurements performed on a real sensor network. The differences between measurements and theory are explained. In case of geograph- ically meaningful sensor data, it is important to have a knowledge of the relative position of each node. In the last part of the paper we present some experimental results of positioning based on the received signal strength indicators (RSSI). As one could expect, the accuracy of such a method is poor, even in a well controlled environment. But the method has some potential.

The increasing use of Unmanned Aerial Vehicles (UAVs) in modern civilian and military applications shows the urgency of having a robust drone detector that detects unseen drone RF signals. Ideally, the system can also classify known RF signals from known drones. This study aims to develop an incremental-learning framework which can classify the known RF signals, and further detect novel RF signals. We propose DE-FEND: a Deep residual network-based autoEncoder FramEwork for known drone signal classification, Novelty Detection, and clustering. The known signal classification and novelty detection are performed in a semi-supervised and unsupervised manner, respectively. We used commercial drone RF signals to evaluate the performance of our framework. With our framework, we obtained 100% novelty detection accuracy at 1.04% False Alarm Rate (FAR) and 97.4% classification accuracy with only 10% labelled samples. Furthermore, we show that our framework outperforms the state-of-the-art (SoA) algorithms in terms of novelty detection performance.

Despite several beneficial applications, unfortunately, drones are also being used for illicit activities such as drug trafficking, firearm smuggling or to impose threats to security-sensitive places like airports and nuclear power plants. The existing drone localization and neutralization technologies work on the assumption that the drone has already been detected and classified. Although we have observed a tremendous advancement in the sensor industry in this decade, there is no robust drone detection and classification method proposed in the literature yet. This paper focuses on radio frequency (RF) based drone detection and classification using the frequency signature of the transmitted signal. We have created a novel drone RF dataset using commercial drones and presented a detailed comparison between a two-stage and combined detection and classification framework. The detection and classification performance of both frameworks are presented for a single-signal and simultaneous multi-signal scenario. With detailed analysis, we show that You Only Look Once (YOLO) framework provides better detection performance compared to the Goodness-of-Fit (GoF) spectrum sensing for a simultaneous multi-signal scenario and good classification performance comparable to Deep Residual Neural Network (DRNN) framework.

Detecting UAVs is becoming more crucial for various industries such as airports and nuclear power plants for improving surveillance and security measures. Exploiting radio frequency (RF) based drone control and communication enables a passive way of drone detection for a wide range of environments and even without favourable line of sight (LOS) conditions. In this paper, we evaluate RF based drone classification performance of various state-of-the-art (SoA) models on a new realistic drone RF dataset. With the help of a newly proposed residual Convolutional Neural Network (CNN) model, we show that the drone RF frequency signatures can be used for effective classification. The robustness of the classifier is evaluated in a multipath environment considering varying Doppler frequencies that may be introduced from a flying drone. We also show that the model achieves better generalization capabilities under different wireless channel and drone speed scenarios. Furthermore, the newly proposed model's classification performance is evaluated on a simultaneous multi-drone scenario. The classifier achieves close to 99% classification accuracy for signal-to-noise ratio (SNR) 0 dB and at -10 dB SNR it obtains 5% better classification accuracy compared to the existing framework.

Video display units (VDUs) using differential signaling technology significantly increase the risk of compromising video information security through leakage emissions. This article shows that differential signaling cables act as substantial video leakage sources. A concept is proposed that explains the video leakage principles of VDUs using differential signal cables such as the high-definition multimedia interface (HDMI) cable, digital visual interface (DVI) cable, and the low-voltage differential signaling (LVDS) cable. The emanations of the LVDS cable are closely examined by measuring simultaneously the differential video signal on the LVDS lines and its near- and far-field leakage emissions. From these measurements, several conclusions are drawn that give new insights into the video eavesdropping risk of VDUs using differential signaling methods. Furthermore, a novel video image reconstruction method is proposed that exploits the compromising emanations of a VDU by using frequency demodulation techniques. This article shows that leaked video emanations of VDUs using differential signaling cables are not only amplitude modulated (AM) but also frequency modulated (FM). This strongly implies that the possible algorithmic toolset of malicious video eavesdroppers is much larger than currently assumed. This article investigates several VDU setups at a distance of 10 m, including an ultrahigh-definition video display, three different HDMI cables and two notebooks. Additionally, the AM-based and FM-based video image reconstruction results are discussed and compared.

In this paper a method is presented which successfully reconstructs the video image of a video display unit (VDU) by exploiting its leakage emissions at a distance of 80 meters. The video image reconstruction is realized without any prior knowledge of the leaking VDU and by using commercial off-the-shelf material. The tested VDUs comprise of an UHD (ultra-high-definition) video display and a full HD (high-definition) video display, both employing an HDMI (high-definition multimedia interface) cable as a video data signaling interface linked to a notebook. The tested setups are located in an urban environment with sporadic radio emissions and occupied frequency bands. Subsequently, the methods and results are thoroughly discussed which give new insights into this video eavesdropping risk for improving video data security.

This paper proposes a method that reconstructs the original video data signal from leaking electromagnetic emanations of multiple video signal sources using a software-defined radio (SDR). The results of the method give valuable insights into the potential risk of this threat of obtaining sensitive information in an everyday situation. The leaking emanations of co-located identical high definition liquid crystal displays are analyzed for possible data reconstruction using a SDR of a small form factor. It is proven that the leaked emanations of multiple identical active video display units (VDUs) can be separated from each other and that their separate video images can be reconstructed individually from one data acquisition. Moreover, this is done by recovering the synchronization frequencies and the image resolution by exploiting multiple leakage channels without having any foreknowledge of the VDU's properties. A multitude of leakage channels is investigated and analyzed for their radiation pattern and their signal-to-noise ratio, and is exploited to increase the quality of the reconstructed images employing multiple-input multiple-output based techniques. As far as we can see, our results and new insights in the nature and mechanisms of multiple compromising emanations are crucial for improving video data security.

One of the problems that we face today is the illegal use of drones. Monitoring the RF transmissions has proved to be a reliable technique for detecting and identifying such devices. Although there are some solutions on the market for detection and jamming, they are not always successful. The aim of this paper is to analyze the typical communications used by drone manufacturers, which usually implement their own algorithms, and to propose a more robust solution that would consider the range of characteristics that these protocols have. A wide-band energy detection with adaptive threshold is used for extracting specifications of some remote control communications that use spread spectrum modulation.

This paper reveals for the first time the possibility of extracting the color information from leaking emanations originating from a video display unit (VDU). First, the video image is reconstructed in grayscale colors by capturing the video leaking emissions without prior knowledge of the leaking VDU. Then, a method is presented which recovers the video colors with an acceptable error margin. Several VDUs are tested for their leakage response which are placed at a distance of 5 to 10 meters from two receiving antennas. Further, a concept is proposed which gives new insights and understandings in why the color can be recovered. A focus is laid on the leakage phenomenon of the LVDS (low-voltage differential signaling) cable and the TMDS (transition-minimized differential signaling) technology employed by most video signaling cables such as the HDMI (high-definition multimedia interface) and DVI (digital visual interface) cable.

Making use of reliable and precise location and tracking systems is essential to save firefighters lives during fire operations and to speed up the rescue intervention. The issue is that Global Navigation Satellite System (GNSS) (e.g., GPS and Galileo) is not always available especially in harsh wireless environments such as inside buildings and in dense forests. This is why GNSS technology needs to be combined with auxiliary sensors like inertial measurement units (IMU) and ultra-wideband (UWB) radios for ranging to enhance the availability and the accuracy of the positioning system. In this paper, we report our work in the scope of the AIOSAT (Autonomous Indoor/Outdoor Safety Tracking System) project, funded under the EU H2020 framework. In this project, the Royal Military Academy (RMA) is responsible for developing a solution to measure inter-distances between firefighters, based on IEEE Std 802.15.4 compliant UWB radios. For these inter-distance measurements, accuracy better than 50 cm is obtained with high availability and robustness. Medium access control based on time division multiple access (TDMA) mechanism is also implemented to solve the conflict to access the UWB channel. As a result, each node in a network can perform range measurements to its neighbors in less than 84 ms. In addition, in this project, we are in charge of developing a long-range narrow-band communication solution based on LoRa and Nb-IoT to report updated positions to the brigade leader and the command center.

In this chapter, two of the major challenges in the application of ground-penetrating radar in humanitarian demining operations are addressed: (i) development and testing of affordable and practical ground penetrating radar (GPR)-based systems, which can be used off-ground and (ii) development of robust signal processing techniques for landmines detection and identification. Different approaches developed at the Royal Military Academy in order to demonstrate the possibility of enhancing close-range landmine detection and identification using ground-penetrating radar under laboratory and outdoor conditions are summarized here. Data acquired using different affordable and practical GPR-based systems are used to validate a number of promising developments in signal processing techniques for target detection and identification. The proposed approaches have been validated with success in laboratory and outdoor conditions and for different scenarios, including antipersonnel, low-metal content landmines, improvised explosive devices and real mine-affected soils.

This paper deals with the jamming attack which may hinder the cognitive radio from efficiently exploiting the spectrum. We model the problem of channel selection as a Markov decision process. We propose a real-time reinforcement learning algorithm based on Q-learning to pro-actively avoid jammed channels. The proposed algorithm is based on wideband spectrum sensing and a greedy policy to learn an efficient real-time strategy. The learning approach is enhanced through cooperation with the receiving CR node based on its sensing results. The algorithm is evaluated through simulations and real measurements with software defined radio equipment. Both simulations and radio measurements reveal that the presented solution achieves a higher packet success rate compared to the classical fixed channel selection and best channel selection without learning. Results are given for various scenarios and diverse jamming strategies.

The principal objective behind the development of passive radio system is to detect and localize mini remotely piloted aircraft systems (RPAS) and their operators in three dimensions (3D). This paper describes the system architecture, detection procedure and intermediate test results. Goodness-of-Fit (GoF) based spectrum sensing is used to detect the frequency of the transmitted signal of mini-RPAS and its controller. The direction of arrival (DoA) is estimated with the MUSIC algorithm. The implementation of GoF-based wideband spectrum sensing and one dimensional DoA estimation including spatial smoothing and automatic source number detection are detailed in this paper. Several test results are presented to validate the real time operation of the passive radio system.

Information processing equipment (IPE) inevitably leaks emissions into the far- and near-field. Most of these leaked emanations originate from logical processes of the IPE itself. Hence by capturing these emanations, sensitive information can be passively obtained without needing physical access to the device. In this research paper, a method is proposed in which the eavesdropping system reconstructs the target display without any prior-knowledge of the system itself. This is realized by retrieving the synchronization information of the IPE using auto-correlation techniques. The method is applicable to both digital and analog based IPE and keeps the portability and cost of the eavesdropping device in mind. Considering that far-field leakages are more practical to pick up than near-field leakages, this paper will only focus on the far-field emanations that originate from the IPE. The emanations of three IPE, a monitor, a laptop and a portable measurement tablet, are tested and analysed for image reconstruction.

Since the jamming attack is one of the most severe threats in cognitive radio networks, we study how Q-learning can be used to pro-actively avoid jammed channels. However, Q-learning needs a long training period to learn the behaviour of the jammer. We take advantage of wideband spectrum sensing to speed up the learning process and we take advantage of the already learned information to minimise the number of collisions with the jammer. The learned anti-jamming strategy depends on the elected reward strategy which reflects the preferences of the cognitive radio. We start with a reward strategy based on the avoidance of the jammed channels, then we propose an amelioration to minimise the number of frequency switches The effectiveness of our proposal is evaluated in the presence of different jamming strategies and compared to the original Q-learning algorithm. We compare also the anti-jamming strategies related to the two proposed reward strategies.

Time synchronization (sync) is a critical part of wireless communication and sensor networks to support applications like MAC scheduling, event detection and positioning. In this paper we propose two solutions for time sync based on one-way exchange of sync packets in a master-slave configuration. First solution is a BLUE estimator based on a precise quadratic clock model that gives good sync accuracy over a long time span. This estimator involves matrix inversion, which is a computationally demanding task for resource constrained devices. For such cases we propose a recursive clock sync scheme based on simple linear clock model that does not require any matrix computation. We evaluated the proposed methods with implementation on a hardware testbed using UWB wireless access technology. The results show that, in case of the recursive solution, it is possible to restrict absolute sync error below a nanosecond for 95% of the time with sync interval of 0.1 s. With the quadratic model based BLUE solution, same performance can be achieved with interval length as big as 0.4 s.

The problem of jammer localization is an important problem in a tactical context. This paper describes a method for multiple jammer localization and transmission power estimation using only received signal strength (RSS) from spectrum sensing devices for radio environment map (REM). This method is able to localize multiple jammers and to estimate their transmission powers in the presence of known transmitters. Simulations show the efficiency of the method compared to existing methods in the literature such as inverse distance weighting (IDW), kriging, or LiveREM.

In cognitive radio, spectrum sensing is one of the most important tasks. In this article, a blind spectrum sensing method based on goodness-of-fit (GoF) test using likelihood ratio (LLR) is studied. In the proposed method, a chi-square distribution is used for GoF testing. The performance of the method is evaluated through Monte Carlo simulations. It is shown that the proposed spectrum sensing method outperforms the GoF test using Anderson Darling (AD) and the conventional energy detection (ED) in case of a limited number of received samples and low signal to noise ratio (SNR). We also evaluate the proposed method in case of a non-Gaussian noise and in case of noise uncertainty. It is shown that the GoF based spectrum sensing methods are less sensitive to both impairments, than the conventional ED. Finally, this paper investigates the influence of the number of samples on the detection performance. The performance difference between the GoF based sensing (LLR and AD) and ED increases with decreasing number of samples for sensing, which makes the proposed method very effective in CR systems with short sensing periods. Keywords—Cognitive Radio; Spectrum Sensing; Goodness of Fit test; Likelihood Ratio; Mixture Gaussian Noise.