The reciprocity of the wireless channel is the basis of the secret key generation on the physical layer as an emerging method for information security enhancement. Due to the duplex mode of communication systems, the channel responses detected by two connected legitimate nodes are not completely reciprocal. In this paper, an efficient physical layer secret key generation scheme is proposed based on an autoencoder to extract reciprocal features from weakly correlated channel estimates. The encoder part after training is equipped at both nodes to generate features for quantization in various channel environments. Simulation results show lower mean squared error (MSE) and better mutual information of the extracted features comparing to the most efficient linear generation method, the principal component analysis (PCA) based one. It reveals the great potential to generate symmetric secret keys with better performance, particularly in low SNR scenarios.
The reciprocity of the wireless channel is the basis of the secret key generation on the physical layer as an emerging method for information security enhancement. Due to the duplex mode of communication systems, the channel responses detected by two connected legitimate nodes are not completely reciprocal. In this paper, an efficient physical layer secret key generation scheme is proposed based on an autoencoder to extract reciprocal features from weakly correlated channel estimates. The encoder part after training is equipped at both nodes to generate features for quantization in various channel environments. Simulation results show lower mean squared error (MSE) and better mutual information of the extracted features comparing to the most efficient linear generation method, the principal component analysis (PCA) based one. It reveals the great potential to generate symmetric secret keys with better performance, particularly in low SNR scenarios.
Physics layer key, as an emerging method to enhance information security, is generated based on the reciprocity and spatial decorrelation of wireless channels. However, due to the half-duplex mode of the communication systems, the channels detected by the legitimate sides are not completely reciprocal. Meanwhile, when the eavesdropper is extremely close to the legitimate side, the spatial correlation could be very strong and threaten the information security. This paper combines the autoencoder and the multi-task learning into a novel physical layer key generation scheme, i.e., Multi-Task Autoencoder (MTAE). MTAE extracts the reciprocal features from the weakly correlated channel estimates of the legitimate sides while reducing its correlation with eavesdropper. Simulation results show good randomness and consistency with the primary keys generated based on MTAE for the legitimate sides, while increasing the difference in the extracted features between eavesdropper and its adjacent node. The proposed method has great potential in scenarios requiring high security.
The reciprocity of wireless channels is a prerequisite for physical layer secret key generation (SKG). However, inherent factors, such as noise, asynchronous observations, and hardware impairments, disrupt the ideal reciprocity in the channel state information (CSI) observed by the two legitimate parties. To address this issue, we propose a mutual information-driven autoencoder (MIAE) architecture to extract reciprocal channel features from the non-ideal channel observations of legitimate parties. MIAE is constructed with an AutoEncoder Network (AENet) and a mutual information neural estimator (MINE). Specifically, AENet employs a structure with dual encoders and a shared decoder. The two encoders, integrated with convolutional block attention modules (CBAMs), are designed to focus on reciprocal features within CSI observations and to compensate for temporal variations caused by asynchronous observations. The shared encoder and the correspondingly designed loss function further concentrate the autoencoder’s reciprocity enhancement capability into the encoders. MINE is integrated into the proposed MIAE to estimate the mutual information between the channel features of the two parties. This estimation is then used to formulate a mutual information loss, which guides the encoders to learn channel features that closely match the optimal distribution, thereby boosting the key generation rate. Furthermore, a complete SKG scheme is designed based on the proposed channel feature extractor, MIAE. Simulation results show that our proposed MIAE can extract channel features with strong reciprocity and thus achieve excellent SKG performance based on the extracted features. The generalization performance of the proposed MIAE architecture for communication scenarios of different scales has also been examined.
Physical layer encryption is a promising solution to provide transmission security for Internet-of-Things (IoT). To realize physical layer encryption, channel state information (CSI) as a random source to generate secret keys should be exploited. The reciprocity of wireless channel between legitimate communication nodes which is typically assumed for time division duplex (TDD) systems, is of critical importance to ensure the consistency in generated keys at two nodes. However, in practical TDD systems, due to the asynchronous measurement of CSI, the receiver noise and the the difference in hardware, etc., the reciprocity of channel measurements between legitimate parties is hard to be guaranteed, which makes physical layer key generation approach infeasible. To address this issue, we propose a wireless key generation scheme based on deep learning techniques. Firstly, a feature extraction network, which consists of two auto-encoders trained jointly, is developed to extract the common feature from the different yet correlated channel observations at two legitimate nodes, which will be used as the source to generate keys. Then a quantizer with an adaptive guard band width is devised to output a binary secret-key sequence from the feature vector. Numerical results show that the proposed scheme achieves remarkable improvement in terms of key disagreement rate (KDR) and key generation rate (KGR) compared existing counterparts in the literature.
As an alternative and appealing approach to providing information security in wireless communication systems, secret key generation at physical layer has demonstrated its potential in terms of efficiency and reliability over traditional cryptographic methods. Without the necessity of a management centre for key distribution or reliance on computational complexity, physical layer key generation protocols enable two wireless entities to extract identical and dynamic keys from the randomness of the wireless channels associated with them.\nIn this thesis, the reliability of secret key generation at the physical layer is examined in practical wireless channels with imperfect channel state information (CSI). Theoretical analyses are provided to relate key match rate with channel's signal-to-noise ratio (SNR), degrees of channel reciprocity, and iterations of information reconciliation.\nIn order to increase key match rate of physical layer secret key generation, improved schemes in the steps of channel estimation and sample quantization are proposed respectively. In the channel estimation step, multiple observations of the wireless channels are integrated with a linear processor to provide a synthesized and more accurate estimation of the wireless channel. In the sample quantization step, a magnitude based quantization method with two thresholds is proposed to quantize partial samples, where specific quantization areas are selected to reduce cross-over errors. Significant improvements in key match rate are proven for both schemes in theoretical analysis and numerical simulations. Key match rate can even achieve 100% in both schemes with the assistance of information reconciliation process.\nIn the end, a practical application of physical layer secret key generation is presented, where dynamic keys extracted from the wireless channels are utilized for securing secret data transmission and providing efficient access control.
Physical-layer secret key generation (PSKG) is a well-known and effective method for boosting wireless security in the Internet of Things (IoT). This technique creates cryptographic keys from correlated wireless channel measurements by taking advantage of the reciprocal nature of uplink and downlink channels. However, in time-division duplex (TDD) systems, issues such as hardware imperfection and noise can disrupt channel reciprocity, making the key generation process more difficult. This paper presents a new PSKG approach that tackles these issues by using deep learning to enhance channel reciprocity, even with imperfect channel state information (CSI). Specifically, a denoising sparse autoencoder (DSAE) is introduced to efficiently learn and extract channel reciprocity features in TDD OFDM systems. Furthermore, this study presents a low-complexity DSAE-based PSKG scheme that utilizes the phase of channel frequency responses (CFR) for key generation. The reported results indicate that the proposed DSAE-based PSKG method notably decreases the key disagreement ratio (KDR) while improving randomness, offering a robust and practical solution for securing wireless communications in IoT environments.
The reciprocity of wireless channel between legitimate nodes is the premise of physical layer security key generation. Deep neural networks provide the non-linear transformation method to extract symmetric keys from reciprocal channel responses and show better freedom and performance than traditional methods. However, the hidden layer output in neural networks is unpredictable and the extracted high-dimensional features can not be estimated in advance, which is difficult to be applied to the key generation in the physical layer. In this paper, the key generation method based on WGAN-GP adversarial autoencoder is proposed to extract features efficiently between legitimate nodes, and the features can be fitted to the Gaussian distribution. Meanwhile, the Wasserstein distance and gradient penalty are applied in the game training to solve the gradient explosion. Compared with the PCA method, the proposed method has higher security key capacity, lower key error rate, and no interaction in the key generation process, which avoids key leakage.