Artificial Intelligence (AI)-native receivers provide lower bit error rate (BER) compared to the traditional receiver, if they are deployed on the same data distribution as their training set. A major research problem is the uncertainty of whether a particularly trained AI-native receiver maintains its superior performance over the traditional receiver in different deployment environments. To this end, we propose VERITAS as a joint measurement-recovery post deployment framework for AI-native transceivers that continuously looks for distribution shifts in the received pilots and triggers finite re-training spurts. VERITAS leverages a novel out-of-distribution algorithm to detect potential changes in the channel profile, transmitter speed, and delay spread. As soon as such a change is detected, a traditional (reference) receiver is activated, which runs for a period of time in parallel to the AI-native receiver. Finally, VERTIAS compares the bit probabilities of the AI-native and the reference receivers for the same received data inputs, and decides whether or not a retraining process needs to be initiated. Our evaluations reveal that VERITAS can detect changes in the channel profile, transmitter speed, and delay spread with 99%, 97%, and 78% accuracies, respectively, followed by timely initiation of retraining for 86%, 93.3%, and 94.8% of inputs in channel profile, transmitter speed, and delay spread test sets, respectively.

Adversarial examples can represent a serious threat to machine learning (ML) algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems (NIDS), they can jeopardize network security. In this work, we aim to mitigate such risks by increasing the robustness of NIDS towards adversarial attacks. To that end, we explore two adversarial methods for generating malicious network traffic. The first method is based on Generative Adversarial Networks (GAN) and the second one is the Fast Gradient Sign Method (FGSM). The adversarial examples generated by these methods are then used to evaluate a novel multilayer defense mechanism, specifically designed to mitigate the vulnerability of ML-based NIDS. Our solution consists of one layer of stacking classifiers and a second layer based on an autoencoder. If the incoming network data are classified as benign by the first layer, the second layer is activated to ensure that the decision made by the stacking classifier is correct. We also incorporated adversarial training to further improve the robustness of our solution. Experiments on two datasets, namely UNSW-NB15 and NSL-KDD, demonstrate that the proposed approach increases resilience to adversarial attacks.

Open RAN (O-RAN) has the potential for revolutionizing not only cellular communication but also spectrum sensing by carefully controlling uplink/downlink traffic in shared spectrum bands. In this paper, we present the design ofSenseORAN, which detects the presence of radar pulses within the Citizens Broadband Radio Service (CBRS) band. SenseORAN is especially useful for scenarios where these pulses (highest priority) are fully overlapping with interfering LTE signals (secondary priority licensee), requiring immediate detection of such an occurrence. This design paradigm of re-using existing cellular infrastructure with ORAN-compliant sensing and communication slices can potentially eliminate the need for dedicated spectrum sensors along the coastline as well as severe restrictions on the transmit power for the LTE operators that are enforced today. Our approach involves a machine learning module deployed as aRadar Detection xAppat the near-Real-Time (near-RT) Radio Access Network (RAN) Intelligent Controller, i.e., near-RT RIC. The base station or gNB (i) uses the you-only-look-once (YOLO)-based machine learning framework that is modified to detect radar signals present within spectrograms generated from I/Q samples collected during the regular uplink cellular operation, and (ii) maintains a list of ‘occupied’ channels in the 3.5 GHz CBRS band that indicate radar presence. Our design is validated with (i) an over the air collected dataset composed of Type 1 radar and standard-compliant LTE waveforms, and (ii) an experimental testbed of SDRs running a complete Open RAN stack with a near-RT RIC implementation integrated with our YOLO-based xApp. We show radar detection accuracy of 100% under SINR conditions ≥ 12 dB after combining 7 spectrograms into a single decision. Furthermore, using testbed results, we demonstrate that the gNB can be reconfigured to avoid radar interference within 866 ms, which represents a reduction of 85.5% over the 60 s response time mandated for pausing cellular operation in detecting radar presence in the CBRS band today.

In IEEE 802.11 WiFi-based waveforms, the receiver performs coarse time and frequency synchronization using the first field of the preamble known as the legacy short training field (L-STF). The L-STF occupies upto 40% of the preamble length and takes upto$32 \mu \text{s}$of airtime. With the goal of reducing communication overhead, we propose a modified waveform, where the preamble length is reduced by eliminating the L-STF. To decode this modified waveform, we propose a neural network (NN)-based scheme called PRONTO that performs coarse time and frequency estimations using other preamble fields, specifically the legacy long training field (L-LTF). Our contributions are threefold: (i) We present PRONTO featuring customized convolutional neural networks (CNNs) for packet detection and coarse carrier frequency offset (CFO) estimation, along with data augmentation steps for robust training. (ii) We propose a generalized decision flow that makes PRONTO compatible with legacy waveforms that include the standard L-STF. (iii) We validate the outcomes on an over-the-air WiFi dataset from a testbed of software defined radios (SDRs). Our evaluations show that PRONTO can perform packet detection with 100% accuracy, and coarse CFO estimation with errors as small as 3%. We demonstrate that PRONTO provides upto 40% preamble length reduction with no bit error rate (BER) degradation. We further show that PRONTO is able to achieve the same performance in new environments without the need to re-train the CNNs. Finally, we experimentally show the speedup achieved by PRONTO through GPU parallelization over the corresponding CPU-only implementations.

Generating custom modulation patterns as well as dynamically varying the mapping of the constellation points to their corresponding bit representations are some existing methods for mitigating eavesdropping attacks. In such cases, the custom symbol to bit mapping needs to be conveyed to the receiver through a secure and reliable channel. Instead of sending the representations of the modified symbols in regular information fields, we propose a machine learning-based approach, in which the modified symbols are encoded in the parameters of a light-weight neural network (NN). This NN is trained at the transmitter-side, sent as a secret key to the receiver, where it serves as a demapping block to recover the received symbols correctly. In addition, this paper explores the role of data augmentation during the training stage to increase the robustness of the NN with respect to the noise in the channel, as well as architecture compression to reduce transmission overhead. We validate the robustness of the proposed NN-based custom-modulation demapping approach by comparing it with demapping of a standard scheme (e.g., 16QAM), which reveals no appreciable loss in performance. We further quantitatively analyze the impact of channel and noise impairments on the demapping performance.

Opening the Citizen Broadband Radio Service (CBRS) band in the US to secondary users offers unprecedented opportunities to LTE and 5G networks, as long as incumbent radar signals are protected from interference. Towards this aim, the US Federal Communications Commission (FCC) requires Environmental Sensing Capabilities (ESCs) to be installed along the coastal regions. Furthermore, FCC mandates that the secondary users transmit with low power levels, such that the aggregated interference and noise power in the vicinity of ESC sensors remains below −109 dBm/MHz. At this interference level, the ESC must detect 99 % of radar pulses with peak power of at least −89 dBm/MHz. In this paper, we design an enhanced ESC sensor, called ESC+, that leverages the deep learning framework called 'you only look once’ (YOLO) for signal detection using spectrograms. We propose a two-stage spectrogram-based coarse and fine signal analysis method for: (i) detecting, and characterizing radar pulses in environments where the aggregated noise and interference level goes beyond FCC restrictions, and (ii) detecting and characterizing other signal types (e.g., 5G and LTE) in the CBRS band, with a goal of determining unauthorized users. We generate a realistic spectrogram dataset in MATLAB consisting of three signal types of radar, 5G, and LTE where the aggregated interference and noise power occurring concurrently with the radar pulse is varied upto −104 dBm/MHz. We show 100% radar pulse detection in interference and noise levels of up to 3 dB higher than what is required today.

Summary Internet of Things (IoT) is a new phenomenon that proposes novel business opportunities. IoT allows the world to be programmable and might provide several benefits for organizations. Based on the IoT survey, cyber‐security issues are among the most extensive and complicated challenges faced by IoT devices. Threat detection is considered a preventive measure against malware threats, ransomware, and attacks, which become more serious each year because of the dramatic rise in malware attacks. This article investigates threat detection techniques that fall into three categories: malware detection, attack detection, and ransomware detection, published from 2017 to August 2021. We examine solutions, techniques, features, classifiers, and tools proposed by IoT researchers. Some questions are proposed, and answering the questions may help the researchers suggest a more efficient solution in future works. Furthermore, the achievement and disadvantages of each study are discussed. Finally, based on the reviewed studies, some open challenges and practical measures to future directions are suggested, worth further studying and researching threat detection techniques in the IoT.

Deep learning methods have been very successful at radio frequency fingerprinting tasks, predicting the identity of transmitting devices with high accuracy. We study radio frequency fingerprinting deployments at resource-constrained edge devices. We use structured pruning to jointly train and sparsify neural networks tailored to edge hardware implementations. We compress convolutional layers by a$27.2\times$factor while incurring a negligible prediction accuracy decrease (less than 1 percent). We demonstrate the efficacy of our approach over multiple edge hardware platforms, including a Samsung Gallaxy S10 phone and a Xilinx-ZCU104 FPGA. Our method yields significant inference speedups,$11.5\times$on the FPGA and$3\times$on the smartphone, as well as high efficiency: the FPGA processing time is$17\times$smaller than in a V100 GPU. To the best of our knowledge, we are the first to explore the possibility of compressing networks for radio frequency fingerprinting; as such, our experiments can be seen as a means of characterizing the informational capacity associated with this specific learning task.

We propose a framework called AirID that identifies friendly/authorized UAVs using RF signals emitted by radios mounted on them through a technique called as RF fingerprinting. Our main contribution is a method of intentionally inserting `signatures' in the transmitted I/Q samples from each UAV, which are detected through a deep convolutional neural network (CNN) at the physical layer, without affecting the ongoing UAV data communication process. Specifically, AirID addresses the challenge of how to overcome the channel-induced perturbations in the transmitted signal that lowers identification accuracy. AirID is implemented using Ettus B200mini Software Defined Radios (SDRs) that serve as both static ground UAV identifiers, as well as mounted on DJI Matrice M100 UAVs to perform the identification collaboratively as an aerial swarm. AirID tackles the well-known problem of low RF fingerprinting accuracy in `train on one day test on another day' conditions as the aerial environment is constantly changing. Results reveal 98% identification accuracy for authorized UAVs, while maintaining a stable communication BER of 10-4for the evaluated cases.

Radio fingerprinting uniquely identifies wireless devices by leveraging tiny hardware-level imperfections inevitably present in off-the-shelf radio circuitry. This way, devices can be directly identified at the physical layer by analyzing the unprocessed received waveform - thus avoiding energy-expensive upper-layer cryptography that resource-challenged embedded devices may not be able to afford. Recent advances have proven that convolutional neural networks (CNNs) - thanks to their multidimensional mappings - can achieve fingerprinting accuracy levels impossible to achieve by traditional low-dimensional algorithms. The same research, however, has also suggested that the wireless channel may negatively impact the accuracy of CNN-based radio fingerprinting algorithms by making device-unique hardware imperfections much harder to recognize.In spite of the growing interest in radio fingerprinting research by academia and DARPA, the wireless research community still lacks (i) a large-scale open dataset for radio fingerprinting collected in diverse environments and rich, diverse, channel conditions; and (ii) a full-fledged, systematic, quantitative investigation of the impact of the wireless channel on the accuracy of CNN-based radio fingerprinting algorithms. The key contribution of this paper is to bridge this gap by (i) collecting and sharing with the community more than 7TB of wireless data obtained from 20 wireless devices with identical RF circuitry (and thus, worst-case scenario for fingerprinting) over the course of several days in (a) an anechoic chamber, (b) in-the-wild testbed, and (c) with cable connections; and (ii) providing a first-of-its-kind evaluation of the impact of the wireless channel on CNN-based fingerprinting algorithms through (a) the 7TB experimental dataset and (b) a 400GB dataset provided by DARPA containing hundreds of thousands of transmissions from thousands of WiFi and ADS-B devices with different SNR conditions. Experimental results conclude that (i) the wireless channel impacts the classification accuracy significantly, i.e., from 85% to 9% and from 30% to 17% in the experimental and DARPA dataset, respectively; and that (ii) equalizing I/Q data can increase the accuracy to a significant extent (i.e., by up to 23%) when the number of devices increases significantly.

Reliability of modern multicore and many-core chips is tightly coupled with the reliability of their on-chip networks. Communication channels in current Network-on-Chips (NoCs) are extremely susceptible to crosstalk faults. In this work, we propose a set of rules for generating classes of crosstalk free coding systems to protect communication channels in NoCs against crosstalk faults. Codewords generated through these rules are free of '101' and '010' bit patterns, which are the main sources of crosstalk faults in NoC communication channels. The proposed rules determine: (1) the weights of different bit positions in a coding system to reach crosstalk free codings, and (2) how the coding might be utilized in an NoC to prevent crosstalk generating bit patterns in NoC channels. Using the proposed set of rules, designers can obtain coding systems which are crosstalk free for any widths of communication channels. Compared to conventional Forbidden Pattern Free (FPF) systems, the proposed methodology is able to provide unique representation to any input values at the lower bound of the codeword lengths. Analyses show that the proposed rules, along with the proposed encoding/decoding mechanisms, are effective in preventing forbidden pattern coding systems for network-on-chips of any arbitrary channel width.