This paper studies the generation of cryptographic keys from wireless channels in light-fidelity (LiFi) networks. Unlike existing studies, we account for several practical considerations (a) realistic indoor multi-user mobility scenarios, (b) non-ideal channel reciprocity given the unique characteristics of the downlink visible light (VL) and uplink infrared (IR) channels, (c) different room occupancy levels, (d) different room layouts, and (e) different receivers’ field-of-view (FoV). Since general channel models in dynamic LiFi networks are inaccurate, we propose a novel deep learning-based framework to generate secret keys with minimal key disagreement rate (KDR) and maximal key generation rate (KGR). However, we find that wireless channels in LiFi networks exhibit different statistical behaviors under various conditions, leading to concept drift in the deep learning model. As a result, key generation suffers from (a) a deterioration in KDR and KGR up to 29% and 38%, respectively, and (b) failing the NIST randomness test. To enable a concept drift aware framework, we propose an adaptive learning strategy using the similarity of channel probability density functions and the mix-of-experts ensemble method. Results show our adaptive learning strategy can achieve stable performance that passes the NIST randomness test and achieves 8% KDR and 89 bits/s KGR for a case of study with 60° FoV.
This paper studies the generation of cryptographic keys from wireless channels in light-fidelity (LiFi) networks. Unlike existing studies, we account for several practical considerations (a) realistic indoor multi-user mobility scenarios, (b) non-ideal channel reciprocity given the unique characteristics of the downlink visible light (VL) and uplink infrared (IR) channels, (c) different room occupancy levels, (d) different room layouts, and (e) different receivers’ field-of-view (FoV). Since general channel models in dynamic LiFi networks are inaccurate, we propose a novel deep learning-based framework to generate secret keys with minimal key disagreement rate (KDR) and maximal key generation rate (KGR). However, we find that wireless channels in LiFi networks exhibit different statistical behaviors under various conditions, leading to concept drift in the deep learning model. As a result, key generation suffers from (a) a deterioration in KDR and KGR up to 29% and 38%, respectively, and (b) failing the NIST randomness test. To enable a concept drift aware framework, we propose an adaptive learning strategy using the similarity of channel probability density functions and the mix-of-experts ensemble method. Results show our adaptive learning strategy can achieve stable performance that passes the NIST randomness test and achieves 8% KDR and 89 bits/s KGR for a case of study with 60° FoV.
This paper explores secret key generation in 5G and beyond LiFi networks using visible light in the downlink and infrared in the uplink. Unlike the existing works, we focus on a realistic indoor environment with multi-user mobility. Given inaccuracies in high-frequency channel models, we introduce the first deep learning model that combines the channel probing and quantization phases to generate initial secret keys with a minimal key disagreement rate (KDR) of 16% between the uplink and downlink, leading to a key generation rate (KGR) of 79 bits/s after information reconciliation. We show that LiFi channel statistics suffer from concept drifts with user density changes in the room. This increases the KDR by 28% - 44% and the generated keys fail to pass the NIST randomness tests. As a countermeasure, we introduce a voting ensemble model that mitigates concept drifts, maintaining a stable 16% KDR, 79 bits/s KGR, and passing NIST tests, despite the varying user densities.
This paper investigates wireless secret key generation in 5G+ indoor LiFi networks operating in the visible light band in the downlink and the infrared band in the uplink. Unlike the existing research, this paper aims to characterize the impact of indoor user mobility on the ability to generate identical secret keys between the user and the base station. Hence, we first generate mobility traces that reflect realistic human behavior in an indoor setup to capture the sensitivity of the optical channels to random blockage and transceiver-misorientation events associated with user mobility. Next, we generate the corresponding channel impulse response and adopt guard band quantization and information reconciliation to extract identical uplink and downlink keys. Then, we examine a set of spatial and temporal features related to the channel probing rate, key disagreement rate, and key generation rate, along with their statistical distributions. Further, we study the randomness of the key following the NIST randomness tests. Our study demonstrated that the handover strategy significantly impacts the randomness of the key and its generation rate.
This paper investigates the vulnerability of wireless secret key generation (WSKG) to eavesdropping by analyzing the channel impulse response (CIR) between a legitimate user and an eavesdropper under various scenarios in dynamic indoor light fidelity (LiFi) networks. These scenarios include (a) different user densities (2, 4, and 8 users), (b) fields of view (FoVs) of30∘,60∘, and90∘, and (c) various room layouts. Results show that higher user densities increase downlink CIR similarity, as users' movement traces become closer. For instance, with eight users and a30∘FoV, CIR similarity peaks at over 85%–95% during entering and exiting stages and remains no less than 40% during wandering. Consequently, an eavesdropper can generate a key with 27%–37% similarity to the legitimate user's key. To mitigate this threat, we propose a novel defense using a generative adversarial network (GAN) trained with crafted uplink CIRs. GANs model the complex statistical properties of legitimate CIRs and generate synthetic noise that mimics environmental and system characteristics without replicating real user CIRs. This prevents eavesdroppers from extracting useful information and avoids privacy concerns linked to handling actual CIR data. Furthermore, traditional reversed CIR methods are less effective in dynamic environments, where conditions change rapidly and are easier to reverse-engineer. Our GAN-generated noise, applied within the defense zone of the legitimate user, reduces CIR similarities from up to 95% to approximately 1%, effectively nullifying key leakage. These findings highlight the potential of GAN-based noise to significantly enhance WSKG security in dynamic indoor LiFi networks.
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.
Secret keys can be generated from reciprocal channels to be used for shared secret key encryption. However, challenges arise in practical scenarios from non-reciprocal measurements of reciprocal channels due to changing channel conditions, hardware inaccuracies and estimation errors resulting in low key generation rate (KGR) and high key disagreement rates (KDR). To combat these practical issues, we propose KNEW Key Generation using NEural Networks from Wireless Channels, which extracts the implicit features of channel in a compressed form to derive keys with high agreement rate. Two Neural Networks (NNs) are trained simultaneously to map each other's channel estimates to a different domain, the latent space, which remains inaccessible to adversaries. The model also minimizes the distance between the latent spaces generated by two trusted pair of nodes, thus improving the KDR. Our simulated results demonstrate that the latent vectors of the legitimate parties are highly correlated yielding high KGR (≈ 64 bits per measurement) and low KDR (<0.05 in most cases). Our experiments with over-the-air signals show that the model can adapt to realistic channels and hardware inaccuracies, yielding over 32 bits of key per channel estimation without any mismatch.
This paper explores the vulnerability of wireless secret key generation (WSKG) to eavesdropping in a dynamic indoor light-fidelity (LiFi) network. It analyzes the channel impulse response (CIR) similarities of two moving user equipments (UEs) across scenarios with two, four, and eight UEs. We observe that as the number of UEs increases, the similarity in CIR also rises, due to the proximal movement patterns among UEs. Specifically, the similarity rate peaks at 70% when eight UEs enter the room; it then drops to 24% during the wandering phase and rises again to 80% as UEs exit the room. Consequently, an eavesdropper among the eight UEs is able to generate 27% of a legitimate UE’s secret key, it significantly reduces the key’s complexity, decreasing the number of possible keys that need to be tested to break the encryption and making it easier to predict the remainder of the key. To mitigate this issue, we introduce a novel approach that utilizes a generative adversarial network (GAN) to artificially manipulate the CIR, thereby reducing the effectiveness of eavesdropping by adding noise into the observed CIR. This method effectively reduces the CIR similarity to a negligible 1%, thus ensuring the integrity of WSKG against eavesdropping threats.