Search

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.

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.

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., Comment: This article has been accepted in the IEEE COMSNETS 2021 for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Astronomers require efficient automated detection and classification pipelines when conducting large-scale surveys of the (optical) sky for variable and transient sources. Such pipelines are fundamentally important, as they permit rapid follow-up and analysis of those detections most likely to be of scientific value. We therefore present a deep learning pipeline based on the convolutional neural network architecture called $\texttt{MeerCRAB}$. It is designed to filter out the so called 'bogus' detections from true astrophysical sources in the transient detection pipeline of the MeerLICHT telescope. Optical candidates are described using a variety of 2D images and numerical features extracted from those images. The relationship between the input images and the target classes is unclear, since the ground truth is poorly defined and often the subject of debate. This makes it difficult to determine which source of information should be used to train a classification algorithm. We therefore used two methods for labelling our data (i) thresholding and (ii) latent class model approaches. We deployed variants of $\texttt{MeerCRAB}$ that employed different network architectures trained using different combinations of input images and training set choices, based on classification labels provided by volunteers. The deepest network worked best with an accuracy of 99.5$\%$ and Matthews correlation coefficient (MCC) value of 0.989. The best model was integrated to the MeerLICHT transient vetting pipeline, enabling the accurate and efficient classification of detected transients that allows researchers to select the most promising candidates for their research goals., 15 pages, 13 figures, Accepted for publication in Experimental Astronomy and appeared in the 3rd Workshop on Machine Learning and the Physical Sciences, NeurIPS 2020

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.

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.

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.