Wireless secret key generation (WSKG) allows efficient key agreement protocols for securing the sixth generation (6G) wireless networks. Nevertheless, due to external adversaries or internal impairments, WSKG schemes might become vulner-able during the randomness distillation, where the legitimate nodes try to observe their source of common randomness. In this paper, we investigate the WSKG scheme with legitimate parties suffering from hardware impairments (HIs), while an active adversary acts as a man-in-the-middle (MiM) via injecting fake pilot signals. We first utilize randomized pilots to overcome the MiM. We also leverage the concept of recurrent neural networks (RNNs) to further enhance the randomness distillation. More specifically, the long short-term memory networks (LSTMs)-as a well-established type of RNNs-are implemented to learn the long-term dependencies between the observations of legitimate parties. The achievable secret key rate (SKR) and the impact of MiM on system's performance are analyzed. Our numerical results verify the performance gain of our proposed learning-based approach compared with the state-of-the-art methods and provide useful insights on system design. We show that our RNN-based approach achieves 30% and 15% improvement in terms of observation mismatches compared with the naïve scheme and the fully-connected benchmarks, respectively.
Wireless secret key generation (WSKG) allows efficient key agreement protocols for securing the sixth generation (6G) wireless networks. Nevertheless, due to external adversaries or internal impairments, WSKG schemes might become vulner-able during the randomness distillation, where the legitimate nodes try to observe their source of common randomness. In this paper, we investigate the WSKG scheme with legitimate parties suffering from hardware impairments (HIs), while an active adversary acts as a man-in-the-middle (MiM) via injecting fake pilot signals. We first utilize randomized pilots to overcome the MiM. We also leverage the concept of recurrent neural networks (RNNs) to further enhance the randomness distillation. More specifically, the long short-term memory networks (LSTMs)-as a well-established type of RNNs-are implemented to learn the long-term dependencies between the observations of legitimate parties. The achievable secret key rate (SKR) and the impact of MiM on system's performance are analyzed. Our numerical results verify the performance gain of our proposed learning-based approach compared with the state-of-the-art methods and provide useful insights on system design. We show that our RNN-based approach achieves 30% and 15% improvement in terms of observation mismatches compared with the naïve scheme and the fully-connected benchmarks, respectively.
Wireless secret key generation (WSKG) facilitates efficient key agreement protocols for securing the sixth generation (6G) wireless networks thanks to its inherently lightweight functionality. Nevertheless, with the existence of adversarial attacks or internal impairments, WSKG can be negatively affected during the randomness distillation, where the legitimate parties measure a source of common randomness. In this paper, we propose a learning-aided approach for cooperative WSKG under man-in-the-middle (MitM) adversarial attack, while the legitimate nodes suffer fromhardware impairments(HIs). The key idea is to process the PHY-attribute data on the application layer via deploying a deep neural network (DNN) to enhance the randomness distillation. This way, we realize a learning-based software-centric security solution. More specifically, we take into account the sequence-type nature of observed data, and propose a DNN comprised ofgated recurrent units(GRUs) to learn the sequence of observations at legitimate endpoints, while the MitM is also alleviated. Our numerical results verify the performance gain of the proposed learning-based approach compared with the state-of-the-arts. Moreover, time and computation complexity of different learning-based models are studied to address the complexity-performance trade-off. Our tests highlight a performance gain of about 43% in terms of mean-square error (MSE) in comparison with a conventional PHY-only scheme.
Wireless secret key generation (W-SKG) from shared randomness (e.g., from the wireless channel fading realizations), is a well established scheme that can be used for session key agreement. W-SKG approaches can be of particular interest in delay constrained wireless networks and notably in the context of ultra reliable low latency communications (URLLC) in beyond fifth generation (B5G) systems. However W- SKG schemes are known to be malleable over the so called "advantage distillation" phase, during which observations of the shared randomness are obtained at the legitimate parties. As an example, an active attacker can act as a man-in- the-middle (MiM) by injecting pilot signals and/or can mount denial of service attacks (DoS) in the form of jamming. This paper investigates the impact of injection and reactive jamming attacks in W-SKG. First, it is demonstrated that injection attacks can be reduced to - potentially less harmful - jamming attacks by pilot randomization; a novel system design with randomized QPSK pilots is presented. Subsequently, the optimal jamming strategy is identified in a block fading additive white Gaussian noise (BF-AWGN) channel in the presence of a reactive jammer, using a game theoretic formulation. It is shown that the impact of a reactive jammer is far more severe than that of a simple proactive jammer.
In this letter, we examine the PHY layer secret key generation (PHY-SKG) scheme in the presence of man-in-the-middle (MiM) adversary, while legitimate parties suffer fromhardware impairments(HIs). Different from previous works on PHY-SKG that consider adversaries who simply try to make an interference in the communication link, the MiM aims to deceive legitimate entities about the source of common randomness. To conquer the MiM attack, legitimate parties utilize randomized pilots (RPs) in our proposed scheme. We analyze the effect of HIs on the performance of system by deriving the achievable secret key rate (SKR). Our results highlight a fundamental limit, as a ceiling phenomena, on the SKR when having practical imperfections. Top-level guidelines for selecting impairment levels along the transceiver chains is also provided to maximize the performance of the PHY-SKG protocol. Our numerical results verify the analytic expressions derived, while providing insights on system design. We show that by properly considering the HIs, about 25% improvement in the SKR is achievable.
Lightweight session key agreement schemes are expected to play a central role in building Internet of things (IoT) security in sixth-generation (6G) networks. A well-established approach deriving from the physical layer is a secret key generation (SKG) from shared randomness (in the form of wireless fading coefficients). However, although practical, SKG schemes have been shown to be vulnerable to active attacks over the initial "advantage distillation" phase, throughout which estimates of the fading coefficients are obtained at the legitimate users. In fact, by injecting carefully designed signals during this phase, a man-in-the-middle (MiM) attack could manipulate and control part of the reconciled bits and thus render SKG vulnerable to brute force attacks. Alternatively, a denial of service attack can be mounted by a reactive jammer. In this paper, we investigate the impact of injection and jamming attacks during the advantage distillation in a multiple-input-multiple-output (MIMO) system. First, we show that a MiM attack can be mounted as long as the attacker has one extra antenna with respect to the legitimate users, and we propose a pilot randomization scheme that allows the legitimate users to successfully reduce the injection attack to a less harmful jamming attack. Secondly, by taking a game-theoretic approach we evaluate the optimal strategies available to the legitimate users in the presence of reactive jammers.
Digital healthcare services are rapidly evolving for new methodologies, including hospital-to-home (H2H) services and intelligent Internet-of-Medical-Things (IIoMT). The sixth generation (6G) technology is considered as the fabric that facilitates the realization of these technologies, creating a paradigm shift towards personalized e-health services. To deal with the high security requirements and the energy constraints of 6G-enabled e-health services, we propose a lightweight learning-based key generation scheme for a pair of wireless-powered nodes in a cooperative communication system, where the legitimate nodes and the intermediate node have low-cost hardware-impaired transceivers. We utilize an echo state network (ESN) to enhance the “randomness distillation” phase, in which the legitimate parties try to obtain a common source of randomness as the raw data for key agreement. The PHY-based observed data is passed to the ESN, containing a reservoir of sparsely connected neurons to compensate for observation mismatches caused by the unbalanced hardware impairments. The output of the ESN can then be utilized to extract the secret key between e-health endpoints. Numerical experiments verify the performance gain of our proposed echo-based approach, resulting in 50% less required inference time compared with a fully-connected neural network (FCNN). Moreover, a performance gain of about 32% in terms of mean-square error (MSE) is achieved compared with a conventional PHY-only scheme.
Reconfigurable intelligent surfaces (RIS) can both help and hinder the physical layer secret key generation (PL-SKG) of communications systems. Whilst a legitimate RIS can yield beneficial impacts, including increased channel randomness to enhance PL-SKG, a malicious RIS can poison legitimate channels and crack almost all existing PL-SKGs. In this work, we propose an adversarial learning framework that addresses Man-in-the-middle RIS (MITM-RIS) eavesdropping which can exist between legitimate parties, namely Alice and Bob. First, the theoretical mutual information gap between legitimate pairs and MITM-RIS is deduced. From this, Alice and Bob leverage adversarial learning to learn a common feature space that assures no mutual information overlap with MITM-RIS. Next, to explain the trained legitimate common feature generator, we aid signal processing interpretation of black-box neural networks using a symbolic explainable AI (xAI) representation. These symbolic terms of dominant neurons aid the engineering of feature designs and the validation of the learned common feature space. Simulation results show that our proposed adversarial learning- and symbolic-based PL-SKGs can achieve high key agreement rates between legitimate users, and is further resistant to an MITM-RIS Eve with the full knowledge of legitimate feature generation (NNs or formulas). This therefore paves the way to secure wireless communications with untrusted reflective devices in future 6G.