Current Issue

25 December 2023, Volume 44 Issue 12

Previous Issue   

Topics: Key Technologies of Spectrum Game in Space-Air-Ground Integrated Networks

Secure and collaborative spectrum sensing scheme based on audit game

Yuntao WANG, Zhou SU, Qichao XU, Yiliang LIU, Haixia PENG, Hao LUAN

2023, 44(12):  1-14.  doi:10.11959/j.issn.1000-436x.2023238

Asbtract ( 775 )   HTML ( 715)   PDF (920KB) ( 912 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

To defend against poisoning attacks and free-riding attacks conducted by malicious sensing terminals in crowd sensing-based collaborative spectrum sensing (CCSS), a novel audit game-based defense scheme was proposed, which combined the pre-deterrence and post-punishment mechanisms.Firstly, considering the audit budget constraint, a mixed-strategy audit game model under incomplete information was designed, which set a penalty strategy to deter malicious collaborators before spectrum sensing, and audited and punished them after the fusion of sensing data.Then, a lightweight audit chain model with on-chain and off-chain collaboration was designed, in which audit evidence was stored in an off-chain data warehouse and its metadata was publicly published on the blockchain.Furthermore, a distributed and intelligent audit algorithm based on reinforcement learning was devised to adaptively seek the approximate mix-strategy equilibrium of the audit game.Simulation results demonstrate that the proposed scheme can quickly obtain the stable and approximately optimal audit strategies and actively suppress the poisoning and free-riding behaviors of malicious collaborators, in comparison with conventional schemes.

Heterogeneous resource cooperative game in space-ground computing power network

Yutong ZHANG, Yuming PENG, Boya DI, Lingyang SONG

2023, 44(12):  15-27.  doi:10.11959/j.issn.1000-436x.2023214

Asbtract ( 127 )   HTML ( 42)   PDF (983KB) ( 159 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

To deal with the resource competition among satellites in the multi-satellite space-ground computing network, a space-ground heterogeneous resource cooperative game mechanism was designed in terms of the computing and spectrum domains.Each satellite published a computing task which was independent of other tasks and relied on UE to generate raw data.By competing the resources of user terminals and UE, the task offloading and processing was achieved.To provide real-time data services, a distributed scheme was proposed based on multi-agent reinforcement learning to coordinate the computing and spectrum resource competition among satellites, thereby minimizing the system latency.Simulation results indicated that, compared with the existing schemes, the proposed algorithm achieves a lower system latency by fully utilizing the computing and spectrum resources and coordinating the resource competition.

Space-time spectrum sharing based on game theory:dynamic access and penalty strategy

Yangyang NIU, Zhiqing WEI, Zhiyong FENG

2023, 44(12):  28-38.  doi:10.11959/j.issn.1000-436x.2023218

Asbtract ( 89 )   HTML ( 25)   PDF (850KB) ( 81 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

To tackle the challenge of inefficient utilization of spatiotemporal spectrum resources in heterogeneous networks, a reliable spectrum sharing strategy based on game theory was proposed for scenarios where multiple secondary users dynamically access through sensing spatiotemporal spectrum opportunities.Firstly, secondary users sensed the activity state of primary users through channel sampling and subsequently seek suitable spatiotemporal spectrum opportunities.Each secondary user aimed to access more spectrum resources while preventing quality degradation between primary users.Consequently, a negotiation of individual utilities between secondary and primary users was needed, in order to reach a mixed Nash equilibrium.When the secondary user's transmission power was abnormal, its behavior would be regarded as a violation.Then, a backoff time compensation algorithm was presented to penalize the secondary users, according to the number of violations and active nodes in the network.Finally, simulation results validate the effectiveness of the spatiotemporal spectrum opportunities sharing strategy with the penalty mechanism.

Distributed robust beamforming algorithm for spectral coexistence in satellite and high altitude platform networks

Zining WANG, Min LIN, Fei LI, Lve HAN, Weiping ZHU

2023, 44(12):  39-49.  doi:10.11959/j.issn.1000-436x.2023211

Asbtract ( 95 )   HTML ( 24)   PDF (941KB) ( 109 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

A distributed robust beamforming (BF) algorithm was proposed to improve spectrum efficiency for an integrated satellite and high altitude platform (HAP) network.Specifically, for the scenario where satellite network and HAP network adopted multicast and NOMA to serve their respective multiple users, an optimization problem was formulated to maximize the sum rate, subject to the rate requirements of both satellite and aerial terminals, and the transmit power budget of satellite and aerial platforms.Then, by considering both the imperfect channel state information (CSI) and the imperfect successive interference cancellation (SIC), S-procedure and sequential convex approximation were adopted to transform the nonconvex problem, and then a distributed BF algorithm using Lagrange duality was proposed to enable the spectral coexistence.Finally, simulation results demonstrate that the proposed algorithm can achieve a similar performance yet at a lower signaling overhead compared with the other existing works.

Papers

Rate splitting based robust secure transmission scheme in RIS-assisted satellite-terrestrial integrated network

Bai ZHAO, Min LIN, Shengjie XIAO, Ming CHENG, Yifan FENG, Lvxi YANG

2023, 44(12):  50-60.  doi:10.11959/j.issn.1000-436x.2023221

Asbtract ( 87 )   HTML ( 27)   PDF (1059KB) ( 128 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Firstly, considering a reconfigurable intelligent surface (RIS) assisted satellite terrestrial integrated network, the satellite employed the rate splitting multiple access technique to serve multiple earth stations in the presence of multiple eavers-droppers(Eves), while the terrestrial network leveraged multicast technique to serve many ground users with the assist of RIS.Secondly, assuming that only the Eves’ imperfect channel state information could be obtained, a joint optimization problem was formulated to minimize the total transmit power, while ensuring the quality-of-service requirement for all users, and adhering to intercept probabilistic constraints.To tackle this noncom vex problem, the S-procedure and the successive convex approximation approach were employed to convert the intercept probabilistic constraints into solved ones.And then a nuclear norm-based penalty function was employed to propose a robust joint algorithm to obtain the robust beamforming weight vectors and transmit power.Finally, the simulation results demonstrate the effectiveness and superiority of the proposed transmission scheme.

LEO satellite constellation design with multi-QoS guarantee for non-terrestrial network

Ruyan WANG, Xianyi YE, Peng HE, Yaping CUI, Dapeng WU, Fedotov Alexander

2023, 44(12):  61-77.  doi:10.11959/j.issn.1000-436x.2023225

Asbtract ( 102 )   HTML ( 28)   PDF (1089KB) ( 172 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

LEO satellite constellation (LSC) offers seamless and fast connectivity for non-terrestrial network (NTN).However, the lack of QoS guarantees for users significantly impacts the performance of the NTN system.Considering multi-QoS metrics, a capacity and downlink budget model for LSC was established, and subsequently, the establishment of inter-satellite links was framed as a link budget issue for the QoS guarantee.The non-dominated sorting genetic algorithm (INSGA-II) with improved crossover and mutation operators was proposed to optimize LSC, aiming to maximize coverage and system capacity while minimizing constellation costs.The numerical results demonstrate that the designed LSC exhibits comparable or superior performance to Telesat and Kepler, and its scale is only 64% of the Kepler system.

Novel direct sequence spread spectrum communication method

Fanglin GU, Jinlin PENG, Yuzhen HUANG, Shengqun CAO, Haitao ZHAO, Jibo WEI

2023, 44(12):  78-85.  doi:10.11959/j.issn.1000-436x.2023233

Asbtract ( 93 )   HTML ( 21)   PDF (780KB) ( 94 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In response to the problem of limited performance and low spectral efficiency in complex multipath environments of traditional direct sequence spread spectrum communication, a cyclic prefix (CP) block transmission structure spread spectrum system with a time-frequency hybrid direct sequence spread spectrum receiver structure was proposed.The system adopted maximum ratio combination (MRC) in the frequency domain to achieve equalization and de-spreading processes simultaneously, while achieving optimal reception performance and omitting the IFFT process to reduce computational complexity significantly.On this basis, it was proposed to replace the m-sequence with the constant amplitude zero auto correlation (CAZAC) sequence as the spread spectrum sequence, which significantly improved the system performance without increasing computational complexity.Finally, a high-speed spread spectrum communication method based on cyclic code shift keying (CCSK) was proposed to solve the problems of low spectrum utilization efficiency and limited transmission rate in traditional direct sequence spread spectrum.By utilizing the property of Fourier transform time-domain cyclic shift, a low implementation complexity CCSK decoding method was designed, which reduced the multiplication number required for CCSK de-spreading by O(N²) reduced to O (Nlog N), greatly reducing resource consume.The simulation results show that compared to existing direct sequence spread spectrum methods, the proposed method achieves approximately 3 dB gain in both Gaussian and complex multipath channel environments.

Multi-agent reinforcement learning based dynamic optimization algorithm of CRE offset for heterogeneous networks

Cheng ZHANG, Jiaye ZHU, Zening LIU, Yongming HUANG

2023, 44(12):  86-98.  doi:10.11959/j.issn.1000-436x.2023235

Asbtract ( 73 )   HTML ( 14)   PDF (927KB) ( 126 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

To cope with the high throughput demand caused by the proliferation of wireless network users, a multi-agent reinforcement learning based dynamic optimization algorithm of cell range expansion (CRE) offset was proposed for interference scenarios in macro-pico heterogeneous networks.Based on the value decomposition network framework of collaborative multi-agent reinforcement learning, a personalized online local decision of CRE offset for all pico-base stations was achieved by reasonably utilizing and interacting the intra-system user distribution and their interference levels among pico-base stations.Simulation results show that the proposed algorithm has significant advantages in increasing system throughput, balancing the throughput of each base station and improving edge-user throughput, compared to CRE=5 dB and distributed Q-learning algorithms.

Short-term prediction network for short-wave MUF based on model-data dual-driven

Junbing LI, Youjun ZENG, Xiaoping ZENG, Guojun LI, Chenxi BAI

2023, 44(12):  99-111.  doi:10.11959/j.issn.1000-436x.2023234

Asbtract ( 76 )   HTML ( 21)   PDF (1110KB) ( 132 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Predicting the maximum available frequency of short-wave communication presents the challenges of low prediction accuracy of classical prediction model methods and difficulty in obtaining training set data for machine learning prediction methods.To address this issue, a model-data dual-driven bidirectional gated recurrent unit (BiGRU) network for short-term prediction of MUF was proposed.On the model-driven, a large-scale dataset generated by the classical MUF prediction model was used as the model-driven training set, and a preliminary network was obtained after joint learning of the 2D CNN and the BiGRU network.On the data-driven, the preliminary network was trained twice using a small-scale measured dataset to obtain the final network CNN-BiGRU-NN.The simulation results show that the proposed network has reduced average root mean squared error (RMSE) at both daily and momentary scales compared with the GRU network, LSTM network and VOACAP model.

Rational-security and fair two-party comparison protocol

Bowen ZHAO, Yao ZHU, Yang XIAO, Qingqi PEI, Xiaoguo LI, Ximeng LIU

2023, 44(12):  112-123.  doi:10.11959/j.issn.1000-436x.2023220

Asbtract ( 91 )   HTML ( 18)   PDF (755KB) ( 84 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Existing secure two-party comparison protocols usually allowed one party (e.g., Alice) to obtain a comparison result first, and then Alice informed the other one (e.g., Bob) of the comparison result.Obviously, if Alice refused or failed to send the comparison result to Bob, Bob learned nothing about the comparison result, which broke the fairness of the two-party comparison protocol.Based on this, a rational-security and fair two-party comparison protocol TEAM was proposed by seamlessly combining the threshold Paillier cryptosystem and game theory.Specifically, a novel secure two-party comparison protocol based on the threshold Paillier cryptosystem was designed and then searched for equilibrium points at which two parties could obtain comparison results.Strict theoretical analysis demonstrate that TEAM guarantees rational two-party to always obtain the comparison result without sacrificing any of their inputs.In other words, TEAM was correct, secure, and fair.In addition, the experimental results show that TEAM improves up to 50 times in terms of efficiency compared with previous methods under the same experimental settings.

Channel estimation for OFDM system based on deep learning

Yun ZHANG, Jing ZHOU, Jingwei HUANG, Shujuan YU, Liya HUANG

2023, 44(12):  124-133.  doi:10.11959/j.issn.1000-436x.2023240

Asbtract ( 121 )   HTML ( 33)   PDF (826KB) ( 95 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

An efficient channel estimation model based on deep learning was proposed for the problems of inter-carrier interference and inter-symbol interference in 5G system signal reception.The estimated channels were obtained through a preliminary estimation at the pilots.And they were treated as low resolution images containing noise, which were input into the channel estimation model.By learning the mapping relationship between the low resolution images and the high resolution images, the noise in input channels was removed, and the high-resolution channel images were restored to obtain the entire channel state information eventually.The simulation results show that the model not only continues the advantages of traditional attention mechanisms in suppressing redundant information, reduces computational overhead, but also achieves good accuracy and robustness, and has good estimation performance for various channels.

Double reputation and multi-angle weight-based cooperative spectrum sensing method against SSDF attacks

Zhiguo SUN, Zhao WANG, Zengmao CHEN, Rongchen SUN

2023, 44(12):  134-145.  doi:10.11959/j.issn.1000-436x.2023213

Asbtract ( 63 )   HTML ( 22)   PDF (950KB) ( 61 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In order to improve the ability of cooperative spectrum sensing to withstand spectrum sensing data falsification (SSDF) attacks, a double reputation and multi-angle weight-based cooperative spectrum sensing (DRMW-CSS) method was proposed.Firstly, a scoring reputation was obtained by multiple iterations of historical local decision results, and an accuracy reputation was calculated on this basis.Secondly, secondary users (SU) were screened by double reputation and multiple reputation thresholds.Then, the impact of SSDF attacks on the screening method was judged and divided into three situations.Finally, the final global decision was made using the corresponding multi-angle weight data fusion decision method according to different situations.Simulation results show that the proposed method has good sensing accuracy when facing SSDF attacks with different attack strategies and probabilities, and has better anti-attack capability compared to traditional methods.

Integrated communication and positioning system enabled by fusing visible light and RF

Yanbing YANG, Chao HU, Bangyan LU, Pinpin ZHANG, Yimao SUN, Guanyu CHEN

2023, 44(12):  146-157.  doi:10.11959/j.issn.1000-436x.2023230

Asbtract ( 100 )   HTML ( 27)   PDF (956KB) ( 79 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Aiming at the problem that in the hybrid visible light and RF network, such as the traditional user switching scheme leveraging received signal strength and ignoring the user switching error rate, a location-based user switching scheme was proposed.Specifically, an integrated communication and positioning system built upon low-cost IoT chip ESP32 was designed, which could fuse both visible light communication downlink and Wi-Fi uplink signals for accurate user location.A communication and positioning integration framework utilizing time-frequency multiplexing was designed, which used a neural network to estimate the user’s position, and the user completed the switching based on the estimated position.In terms of communication, the throughput of the system can reach up to 35 kbit/s.In terms of positioning, the positioning accuracy of the system can reach 2.8 cm, making a 33% improvement over traditional system.Compared with the switching scheme relying on received signal strength, user switching error rate of the proposed scheme is reduced by 4%.

Multi-ciphertext batch auditable decryption outsourcing SM9-HIBE key encapsulation mechanism

Kuan LIU, Jianting NING, Wei WU, Shengmin XU, Chao LIN

2023, 44(12):  158-170.  doi:10.11959/j.issn.1000-436x.2023222

Asbtract ( 72 )   HTML ( 15)   PDF (836KB) ( 119 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The decryption operation of SM9-HIBE key encapsulation mechanism required two bilinear pairing operations, for the equipment requiring frequent decryption of massive data and with limited computing resources, such resourcing-consuming pairing operation will become an important bottleneck restricting the system deployment.To address the above issue, a decryption outsourcing key encapsulation mechanism OASM9-HIBE based on SM9-HIBE was proposed, which supported multi-ciphertext batch auditing.The Fujisaki-Okamoto transformation technology was utilized to prove the RCCA security of OASM9-HIBE under the random oracle model.All resourcing-consuming bilinear pairing operations were safely offloaded to the cloud server in OASM9-HIBE, the k-th hierarchical user only need to perform one simple exponentiation operation to complete the final decryption.The decryption efficiency of the original SM9-HIBE was effectively improved under the premise of not changing the downward proxy generation function of the user’s private key between hierarchical.OASM9-HIBE additively achieved the property of batch auditing of multi-transformed ciphertexts by employing the key blinding technology.Theoretical analysis and evaluation of experimental data highlight the feasibility and efficiency of OASM9-HIBE, OASM9-HIBE extends the application field of SM9 series algorithms.

Massive unsourced multiple access scheme based on block sequence codebook and compressed sensing

Jing ZHANG, Lin MA, Chulong LIANG, Hongxu GAO

2023, 44(12):  171-180.  doi:10.11959/j.issn.1000-436x.2023239

Asbtract ( 52 )   HTML ( 11)   PDF (836KB) ( 75 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

A massive unsourced multiple access scheme based on block sequence codebook and compressed sensing was proposed for sporadic burst scenario in massive machine type communication (mMTC).Firstly, a large-capacity spreading codebook generation scheme was designed according to a specific shift pattern, thus the codebook space was expanded.Secondly, the sparse structure of uplink signal was combined with multi-carrier technology to support overlapping transmission of multi-user data on some subcarriers, thus the spectral efficiency was improved.Finally, a multi-carrier CS-MUD model was established, and a group orthogonal matching pursuit algorithm based on codebook sequence blocks was designed to achieve the joint detection of active users and their uplink data.Simulation results show that the proposed scheme can effectively reduce the bit error rate of massive random access.

3D WSN clustering routing algorithm based on IHBA optimized fuzzy C-means

Jing YANG, Biyang XU, Weizheng LI, Wei LI, Zhaoqiang ZHU, Tao QIN

2023, 44(12):  181-192.  doi:10.11959/j.issn.1000-436x.2023236

Asbtract ( 59 )   HTML ( 17)   PDF (1009KB) ( 78 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Aiming at the problem that clustering routing algorithm in a three-dimensional (3D) scene has high energy consumption and short network lifetime, a clustering routing algorithm IFCRA for 3D wireless sensor networks based on improved honey badger algorithm optimized fuzzy C-means was proposed.The network clustering, cluster head election, and data transmission stages were optimized respectively.Firstly, the improved honey badger algorithm was used to optimize the fuzzy C-means algorithm, solving the problem of fuzzy C-means easily falling into local optima, and the topological structure was divided based on the distance and energy characteristics of nodes.Secondly, the optimal cluster head function was constructed by combining the energy and relative distance of nodes within the cluster to balance the cluster head load.Finally, an adaptive transmission mechanism was used to search for relay nodes, and the optimal transmission path function was constructed by combining node distance and energy.The improved honey badger algorithm was used to optimize the data transmission energy consumption.Simulation results show that IFCRA has reasonable clustering, balanced energy consumption, and long lifespan in a 3D heterogeneous scene.

Indoor terminal localization technology using a single access point based on distributed MIMO networks

Ze LI, Jian ZOU, Zeng HUANG, Zengshan TIAN

2023, 44(12):  193-205.  doi:10.11959/j.issn.1000-436x.2023237

Asbtract ( 72 )   HTML ( 19)   PDF (1225KB) ( 99 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Regarding the terminal localization in distributed MIMO networks, an indoor terminal localization system using a single access point (AP) based on distributed MIMO networks was proposed.Firstly, the AP’s antennas were arranged at different locations in the room, and the compressed sensing algorithm was used to estimate the angle of departure (AoD) and time of flight (ToF) of the receiving path on each antenna of the terminal device.Secondly, AoDs and ToFs of multiple paths were combined to establish a nonlinear localization model, and an improved Levenberg-Marquardt algorithm was used to solve the problem.Then, theoretical analysis has been examined for the factors that influence the localization error, and the criteria for the antenna layout was provided.Finally, electromagnetic simulation software was used to build simulation environment and conducted the simulation for system verification.Moreover, software-defined radio platforms were used to conduct practical tests.Both simulation and experimental results indicate that the performance of the proposed localization system is superior to existing single-AP localization systems based on natural multipath.

Comprehensive Review

Statistical analysis on application and funding of the National Natural Science Foundation of China in the area of “information and communication systems” in 2023

Ling SUN, Jie HU, Yongcheng LI, Jun WEN, Jie HE, Ke LIU

2023, 44(12):  206-215.  doi:10.11959/j.issn.1000-436x.2023224

Asbtract ( 160 )   HTML ( 49)   PDF (1014KB) ( 194 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

The application and funding of the National Natural Science Foundation of China (NSFC) in the area of information and communication system and in the year of 2023 were statistically analyzed, which included general programs, young scientists funds, funds for developing regions, key program, excellent and outstanding young scholar funds.The research teams, research trends in information and communication system during the Fourteenth Five-Year Plan were introduced.Since general programs and young scientists funds receive the highest volume of applications, detailed statistics were further provided among different institutions and application codes.Then the statistics of application and funding results with different attributes of scientific problems were presented.Finally, the result of responsibility-credit-contribution (RCC) evaluation mechanism on the reviewing process was provided.

Correspondences

Double-component combined generalized weighted fractional Fourier transform based waveform design for massive MIMO

Xingjian LI, Zhiqun SONG, Yong LI, Lizhe LIU, Bin WANG, Chang WANG

2023, 44(12):  216-229.  doi:10.11959/j.issn.1000-436x.2023226

Asbtract ( 55 )   HTML ( 16)   PDF (940KB) ( 108 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In order to overcome the drawback of conventional diversity technologies that sacrificing valuable communication resources such as data rate or bandwidth in massive multiple input multiple output (MIMO) systems, a double-component combined generalized weighted fractional Fourier transform (DCGWFRFT) based waveform design method was proposed.The concept of computational diversity was introduced, and the diversity performance was improved via moderate computational resources without requiring channel state information at the transmitter.The principle of computational diversity of DCGWFRFT based waveform was firstly analyzed, and a DCGWFRFT based waveform design and transform process, which could be adopted combined with existing diversity methods, was then proposed according to the principle.Theoretical analysis proves that the proposed waveform design and transform process can perfectly recover the original transmitted signal in noise-free case, and the power of error of proposed waveform is distributed more evenly than that of untransformed waveform in noisy case.Simulation results show that the performance of DCGWFRFT based waveform has an advantage of at least 1.7 dB in bit signal-to-noise ratio compared with untransformed waveform when bit error rate is 10^-3.

Secure federated distillation GAN for CIDS in industrial CPS

Junwei LIANG, Geng YANG, Maode MA, Sadiq Muhammad

2023, 44(12):  230-244.  doi:10.11959/j.issn.1000-436x.2023216

Asbtract ( 87 )   HTML ( 25)   PDF (1039KB) ( 162 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Aiming at the data island problem caused by the imperativeness of confidentiality of sensitive information, a secure and collaborative intrusion detection system (CIDS) for industrial cyber physical systems (CPS) was proposed, called PFD-GAN.Specifically, a novel semi-supervised intrusion detection model was firstly developed by improving external classifier-generative adversarial network (EC-GAN) with Wasserstein distance and label condition, to strengthen the classification performance through the use of synthetic data.Furthermore, local differential privacy (LDP) technology was incorporated into the training process of developed EC-GAN to prevent sensitive information leakage and ensure privacy and security in collaboration.Moreover, a decentralized federated distillation (DFD)-based collaboration was designed, allowing multiple industrial CPS to collectively build a comprehensive intrusion detection system (IDS) to recognize the threats under the entire cyber systems without sharing a uniform template model.Experimental evaluation and theory analysis demonstrate that the proposed PFD-GAN is secure from the threats of privacy leaking and highly effective in detecting various types of attacks on industrial CPS.