Browsing by Author "Wang, Liang"

Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    Deep reinforcement learning-based long-range autonomous valet parking for smart cities
    (Elsevier, 2022-11-25) Khalid, Muhammad; Wang, Liang; Wang, Kezhi; Aslam, Nauman; Pan, Cunhua; Cao, Yue
    In this paper, to reduce the congestion rate at the city center and increase the traveling quality of experience (QoE) of each user, the framework of long-range autonomous valet parking is presented. Here, an Autonomous Vehicle (AV) is deployed to pick up, and drop off users at their required spots, and then drive to the car park around well-organized places of city autonomously. In this framework, we aim to minimize the overall distance of AV, while guarantee all users are served with great QoE, i.e., picking up, and dropping off users at their required spots through optimizing the path planning of the AV and number of serving time slots. To this end, we first present a learning-based algorithm, which is named as Double-Layer Ant Colony Optimization (DLACO) algorithm to solve the above problem in an iterative way. Then, to make the fast decision, while considers the dynamic environment (i.e., the AV may pick up and drop off users from different locations), we further present a deep reinforcement learning-based algorithm, i.e., Deep Q-learning Network (DQN) to solve this problem. Experimental results show that the DL-ACO and DQN-based algorithms both achieve the considerable performance.
  • Thumbnail Image
    ItemOpen Access
    Graph layer security: encrypting information via common networked physics
    (MDPI, 2022-05-23) Wei, Zhuangkun; Wang, Liang; Sun, Schyler Chengyao; Li, Bin; Guo, Weisi
    The proliferation of low-cost Internet of Things (IoT) devices has led to a race between wireless security and channel attacks. Traditional cryptography requires high computational power and is not suitable for low-power IoT scenarios. Whilst recently developed physical layer security (PLS) can exploit common wireless channel state information (CSI), its sensitivity to channel estimation makes them vulnerable to attacks. In this work, we exploit an alternative common physics shared between IoT transceivers: the monitored channel-irrelevant physical networked dynamics (e.g., water/oil/gas/electrical signal-flows). Leveraging this, we propose, for the first time, graph layer security (GLS), by exploiting the dependency in physical dynamics among network nodes for information encryption and decryption. A graph Fourier transform (GFT) operator is used to characterise such dependency into a graph-bandlimited subspace, which allows the generation of channel-irrelevant cipher keys by maximising the secrecy rate. We evaluate our GLS against designed active and passive attackers, using IEEE 39-Bus system. Results demonstrate that GLS is not reliant on wireless CSI, and can combat attackers that have partial networked dynamic knowledge (realistic access to full dynamic and critical nodes remains challenging). We believe this novel GLS has widespread applicability in secure health monitoring and for digital twins in adversarial radio environments.
  • Thumbnail Image
    ItemOpen Access
    Multi-agent deep reinforcement learning-based key generation for graph layer security
    (Association for Computing Machinery (ACM), 2025-05) Wang, Liang; Wei, Zhuangkun; Guo, Weisi
    Recently, the emergence of Internet of Things (IoT) devices has posed a challenge for securing information and avoiding attacks. Most of the cryptography solutions are based on physical layer security (PLS), whose idea is to fully exploit the properties of wireless channel state information (CSI) for generating symmetric keys between two communication nodes. However, accurate channel estimation is vulnerable for attackers and relies on powerful signal processing capability, which is not suitable for low-power IoT devices. In this paper, we expect to apply graph layer security (GLS) to exploit the common features of physical dynamics detected by IoT sensors placed in networked systems to generate keys for data encryption and decryption, which we believe is a new frontier to security for both industry and academic research. We propose a distributed key generation algorithm based on multi-agent deep reinforcement learning (MADRL) approach, which enables communication nodes to cooperatively generate symmetric keys based on their locally detected physical dynamics (e.g., water/gas/oil/electrical pressure/flow/voltage) with low computational complexity and without information exchange. In order to demonstrate the feasibility, we conduct and evaluate our key generation algorithm in both a simulated and real water distribution network. The experimental results show that the proposed algorithm has considerable performance in terms of randomness, bit agreement rate (BAR), and so on.
  • Thumbnail Image
    ItemOpen Access
    Secret key rate upper-bound for reconfigurable intelligent surface-combined system under spoofing
    (IEEE, 2023-01-18) Wei, Zhuangkun; Wang, Liang; Guo, Weisi
    Reconfigurable intelligent surfaces (RIS) have been shown to improve the secret key rate (SKR) for physical layer secret key generation (PL-SKG), by using the programmable phase shifts to increase reciprocal channel entropy. Most current studies consider the role of RIS on passive eavesdroppers (Eves) and overlook active attackers, especially the pilot spoofing attacks (PSA). For PSA in PL-SKG setups, this is implemented by Eve sending an amplified pilot sequence simultaneously with legitimate user Alice. With the increase of the spoofing amplifying factor, the channel probing results at Bob and Eve become similar, thereby enabling Eve to generate shared secret key with Bob. In this work, we analyze how RIS can positively or negatively affect the PL-SKG under pilot spoofing. To do so, we theoretically express the legitimate and spoofing SKRs in terms of the RIS phase shifts. Leveraging this, the closed-form theoretical upper bounds of both legitimate and spoofing SKRs are deduced, which lead to two further findings. First, the legitimate SKR upper-bound does not vary with RIS phase shift vector, but reduces drastically with the increase of the spoofing amplifying factor. This suggests the limited effect of RIS against PL-SKG spoofing, since the legitimate SKR has a hard limit, which cannot be surpassed by adjusting RIS phase and reflecting power, but can even be 0 with properly assigned spoofing amplifying factor. Second, the spoofing SKR upper-bound shows a large gap from the non-optimized SKR, which indicates a potential for RIS phase optimization.