In this paper, a machine learning (ML) approach is proposed to detect and classify jamming attacks against orthogonal frequency division multiplexing (OFDM) receivers with applications to unmanned aerial vehicles (UAVs). Using software-defined radio (SDR), four types of jamming attacks; namely, barrage, protocol-aware, single-tone, and successive-pulse are launched and investigated. Each type is qualitatively evaluated considering jamming range, launch complexity, and attack severity. Then, a systematic testing procedure is established by placing an SDR in the vicinity of a UAV (i.e., drone) to extract radiometric features before and after a jamming attack is launched. Numeric features that include signal-to-noise ratio (SNR), energy threshold, and key OFDM parameters are used to develop a feature-based classification model via conventional ML algorithms. Furthermore, spectrogram images collected following the same testing procedure are exploited to build a spectrogram-based classification model via state-of-the-art deep learning algorithms (i.e., convolutional neural networks). The performance of both types of algorithms is analyzed quantitatively with metrics including detection and false alarm rates. Results show that the spectrogram-based model classifies jamming with an accuracy of 99.79% and a false-alarm of 0.03%, in comparison to 92.20% and 1.35%, respectively, with the feature-based counterpart.

GPS spoofing attacks are a severe threat to unmanned aerial vehicles. These attacks manipulate the true state of the unmanned aerial vehicles, potentially misleading the system without raising alarms. Several techniques, including machine learning, have been proposed to detect these attacks. Most of the studies applied machine learning models without identifying the best hyperparameters, using feature selection and importance techniques, and ensuring that the used dataset is unbiased and balanced. However, no current studies have discussed the impact of model parameters and dataset characteristics on the performance of machine learning models; therefore, this paper fills this gap by evaluating the impact of hyperparameters, regularization parameters, dataset size, correlated features, and imbalanced datasets on the performance of six most commonly known machine learning techniques. These models are Classification and Regression Decision Tree, Artificial Neural Network, Random Forest, Logistic Regression, Gaussian Naïve Bayes, and Support Vector Machine. Thirteen features extracted from legitimate and simulated GPS attack signals are used to perform this investigation. The evaluation was performed in terms of four metrics: accuracy, probability of misdetection, probability of false alarm, and probability of detection. The results indicate that hyperparameters, regularization parameters, correlated features, dataset size, and imbalanced datasets adversely affect a machine learning model’s performance. The results also show that the Classification and Regression Decision Tree classifier has an accuracy of 99.99%, a probability of detection of 99.98%, a probability of misdetection of 0.2%, and a probability of false alarm of 1.005%, after removing correlated features and using tuned parameters in a balanced dataset. Random Forest can achieve an accuracy of 99.94%, a probability of detection of 99.6%, a probability of misdetection of 0.4%, and a probability of false alarm of 1.01% in similar conditions.

Remote Keyless Entry (RKE) systems are essential in modern lifestyle with applications including vehicle and garage entry. However, the convenience such systems facilitate comes at the expense of their vulnerability to different attacks such as jamming, replay, jamming-and-replay, and cryptanalysis. These attacks, if lightly taken, may lead to catastrophic consequences to the general public, such as property theft and human casualties. To this end, an improved RKE system using timestamping and XOR encoding is proposed to countermeasure the aforementioned attacks. In addition, the integrated defense mechanism protects the authentication code in scenarios where the encrypted transmitter-receiver communications is compromised. The defense mechanism in the proposed RKE is demonstrated and tested in realistic setups, and is found to outperform the conventional RKE.

We propose a new methodology for the design of a dual-band unequal-split Wilkinson power divider (WPD) with a high power division ratio at the operating frequencies. Impractical high-impedance transmission line in the conventional divider is replaced with cascaded dual-band T-section structures based on analytical equations derived herein. To validate the design concept, a dual-band WPD operating at 1 and 2 GHz with a 1:10 split ratio is simulated and measured. Simulations and measurements show isolation and input-output ports matching better than -20 dB, and transmission parameters, S₂₁ and S₂₁, of -10.5 ± 0.5 dB and -0.4 ± 0.5 dB at the design bands, respectively.

The establishment of convenient and reliable cryptographic keys is not always feasible, especially in low-powered wireless devices where a complex key management infrastructure is unaffordable. Physical layer-based key generation approaches, on the other hand, allow two legitimate users to establish a common secret key by exploiting the parameters of the wireless channel, such as the underlying impulse response. In this paper, a fundamental bound on the maximum achievable key generation rate (KGR) over wireless fading channels with asymmetric additive white Gaussian noise (AWGN) is derived. A Nakagamim fading channel is considered, and the effect of non-reciprocity on the forward and reverse channels correlation is demonstrated. We validate the theoretical platform through simulations using a key generation protocol based on the level crossing rate (LCR) of the fading process. The proposed LCR protocol models the Nakagami channel by utilizing the sum-of-sinusoids approach, where Doppler shift, fading severity, and number-of-paths are taken into account. The proposed protocol also incorporates a two-level quantizer to extract keys, where the channel estimates between a wireless transmitter and receiver can be used as the basis. Besides providing an upper bound on the KGR, the analytical and simulation results intertwine the effect of channel reciprocity with the key generation process.