Most of the traditional cryptanalytic technologies often require a great amount of time, known plaintexts, and memory. This paper proposes a generic cryptanalysis model based on deep learning (DL), where the model tries to find the key of block ciphers from known plaintext-ciphertext pairs. We show the feasibility of the DL-based cryptanalysis by attacking on lightweight block ciphers such as simplified DES, Simon, and Speck. The results show that the DL-based cryptanalysis can successfully recover the key bits when the keyspace is restricted to 64 ASCII characters. The traditional cryptanalysis is generally performed without the keyspace restriction, but only reduced-round variants of Simon and Speck are successfully attacked. Although a text-based key is applied, the proposed DL-based cryptanalysis can successfully break the full rounds of Simon32/64 and Speck32/64. The results indicate that the DL technology can be a useful tool for the cryptanalysis of block ciphers when the keyspace is restricted.

Recently, with the development of autonomous driving technology, vehicle-to-everything (V2X) communication technology that provides a wireless connection between vehicles, pedestrians, and roadside base stations has gained significant attention. Vehicle-to-vehicle (V2V) communication should provide low-latency and highly reliable services through direct communication between vehicles, improving safety. In particular, as the number of vehicles increases, efficient radio resource management becomes more important. In this paper, we propose a deep reinforcement learning (DRL)-based decentralized resource allocation scheme in the V2X communication network in which the radio resources are shared between the V2V and vehicle-to-infrastructure (V2I) networks. Here, a deep Q-network (DQN) is utilized to find the resource blocks and transmit power of vehicles in the V2V network to maximize the sum rate of the V2I and V2V links while reducing the power consumption and latency of V2V links. The DQN also uses the channel state information, the signal-to-interference-plus-noise ratio (SINR) of V2I and V2V links, and the latency constraints of vehicles to find the optimal resource allocation scheme. The proposed DQN-based resource allocation scheme ensures energy-efficient transmissions that satisfy the latency constraints for V2V links while reducing the interference of the V2V network to the V2I network. We evaluate the performance of the proposed scheme in terms of the sum rate of the V2X network, the average power consumption of V2V links, and the average outage probability of V2V links using a case study in Manhattan with nine blocks of 3GPP TR 36.885. The simulation results show that the proposed scheme greatly reduces the transmit power of V2V links when compared to the conventional reinforcement learning-based resource allocation scheme without sacrificing the sum rate of the V2X network or the outage probability of V2V links.

Massive multiple-input multiple-output (MIMO) is one of the most promising technologies for a user equipment (UE) to achieve a high data rate. However, massive MIMO requires channel state information (CSI) at the transmitter and the CSI overhead fed back by UEs exponentially increases as the number of antennas increases. In the last years, many studies have been conducted to solve the problem of enormous CSI feedback overhead by utilizing deep learning. In this letter, we propose an adaptive lightweight convolutional neural network (CNN) in the deep learning-based MIMO CSI feedback. The proposed network adaptively finds the compression ratio to be used in the network and reduces the computational complexity of the network. Simulation results show that the proposed lightweight CNN significantly reduces the computational complexity in comparison with the conventional CsiNet while achieving the equivalent performance; and moreover the proposed network converges faster.

A new interference‐aware frequency hopping (IAFH) scheme for Bluetooth to mitigate the interference from Wi‐Fi networks is proposed. The conventional adaptive frequency hopping (AFH) scheme classifies channels into ‘good’ or ‘bad’ according to the predefined threshold and uses good channels with a uniform hop probability. Unlike the conventional AFH scheme, the proposed IAFH dynamically classifies channels into ‘good’ or ‘bad’ according to the observed interference levels and uses good channels with non‐uniform hop probabilities. The simulation results demonstrate that the proposed IAFH scheme significantly outperforms the conventional AFH scheme.

In cooperative spectrum sensing (CSS), a multibit combination rule shows better sensing performance than one-bit hard combination rules at the sacrifice of the reporting overhead. To overcome the tradeoff between the sensing performance and the reporting overhead, we propose a novel group-based multibit CSS scheme with a limited reporting overhead. The proposed scheme adopts contention-based reporting to restrain the reporting overhead while achieving multiuser diversity with an increased number of secondary users (SUs). Moreover, SUs report one-bit sensing results to a fusion center instead of sending multibit quantization information, and the rest of the information is embedded in the time slot. The simulation results demonstrate that, as the number of SUs increases, the proposed scheme improves the sensing performance and the average throughput of SUs, whereas the conventional one-bit or multibit combination schemes show a tradeoff between the sensing performance and the throughput of SUs.