Categories
Engineering and Technologies

Engineering and Technologies

Security and Privacy for 6G: A Survey on Prospective Technologies and Challenges

Security and Privacy for 6G: A Survey on Prospective Technologies and Challenges

Jul 14, 2025

Introduction           Sixth-generation (6G) mobile networks will have to cope with diverse threats on a space-air-ground integrated network environment, novel technologies, and an accessible user information explosion. However, for now, security and privacy issues for 6G remain largely in concept. Inspired by security evolution in prior generations, this work provides a systematic review of existing research efforts on security and privacy for 6G networks. The article reviews the issues of 6G enabling technologies and state-of-the-art defense methods. By conducting the problems in each technology, our goal is to provide a holistic view of the evolution of core security and privacy issues, along with the remaining challenges for further enhancements. To this end, the study aims to answer the fundamental question: What are the major potential changes of 6G security infrastructure from the prior generations? What are new challenges and prospective approaches for privacy preservation in 6G to satisfy the requirements in laws, such as General Data Protection Regulation (GDPR)? The main contributions of this article are multi-fold. First, the work provides a systematic overview of the evolution of security architecture and vulnerabilities in legacy networks. By investigating the shortcomings of the standards and technical insights of protocol flaws in such networks, required enhancements to 6G security and privacy are highlighted. Second, our survey provides a holistic view of security and privacy issues and how the existing solutions must be changed to satisfy the new demands in 6G. Since 6G will continue on the techno-economic trajectory of 5G, a systematic review on transition and possible changes of 6G security and privacy can shed light on the best plan for the operators/developers to upgrade the security infrastructure/defense systems at the right time. Finally, our discussions about lessons learned from the shortcomings of existing security architecture and remaining technical challenges may help researchers/developers quickly identify relevant issues and starting points for further works. The key security aspects are summarized in Figure 1.   Figure 1. A taxonomy of key points of our survey on security & privacy for 6G   Key findings from the research:      1. Major differences between 5G and 6G:  5G introduced substantial advancements like improved subscriber identity protection through SUCI (Subscription Concealed Identifier), and basic AI-assisted threat detection, it still carries many vulnerabilities, including weaknesses in mutual authentication, susceptibility to fake base stations, and the reuse of legacy protocols that expose outdated threats. In contrast, 6G security is envisioned to go far beyond patching existing flaws. It will operate in a space-air-ground-sea integrated network environment with radically diverse applications such as brain-computer interfaces, holographic telepresence, and autonomous systems. However, new technologies mean novel vulnerabilities. Unlike 5G, 6G will incorporate quantum-safe cryptography, AI-empowered real-time adaptive security, and physical layer security in beamforming and directional communications that leverages wireless channel characteristics. Also, unlike 5G’s centralized identity model, 6G may move toward decentralized, passwordless authentication through biometrics and system-on-chip identities. Blockchain and distributed ledgers are also considered for ensuring data integrity and mutual trust across domains. Furthermore, 6G networks are expected to fully support real-time zero-touch threat responses and zero-trust architectures, emphasizing dynamic, policy-based access control. This leap from static protection models to intelligent, self-defending infrastructures marks a transformative shift from 5G’s reactive posture to 6G’s proactive and predictive security paradigm. A summary of typical 6G vs 5G applications and security requirements is illustrated in Figure 2. 6G security will upgrade 5G security with new capability in terms of intelligence, automation, and energy efficiency. Figure 2. 6G security vs 5G security.         2. Space-Air-Ground-Sea Integrated Networks will be the next frontier of security defense, probably national security: As the rising popularity of satellite-based broadband networks and drones in civil applications, Space-Air-Ground-Sea Integrated Networks (SAGIN) will be the reachable target of mobile networks in the coming years. By combining terrestrial, aerial, maritime, and satellite systems, 6G SAGIN will achieve expansive coverage and support critical applications like emergency rescue and autonomous navigation. However, this integration introduces heightened risks, including jamming, eavesdropping, and masquerading attacks on high-altitude platforms. Given the strategic relevance of SAGIN infrastructure for national defense, public safety, and global communications, securing it becomes essential. Further research on efficient and secure SAGIN models for national targets will be critical.      3. AI-based functions in 6G will be the new target of the tit-for-tat battle between attackers and security defenders: AI-based functions in 6G are expected to revolutionize network operations through automation, real-time decision-making, and adaptive security responses. However, this reliance on AI introduces a new battleground where attackers and defenders will continually outmaneuver each other. Adversaries may exploit vulnerabilities in AI models, such as data poisoning or adversarial inputs, to mislead or disable security mechanisms. Meanwhile, defenders must develop more robust, transparent, and resilient AI systems to detect and neutralize evolving threats. This cat-and-mouse dynamic will define the future of 6G security, demanding continuous innovation to stay ahead of increasingly intelligent and adaptive cyberattacks. Figure 3 summarizes key attacks and defense approaches for AI-based functions and case studies in 6G. Figure 3. Attack and defense methods in AI-based functions for 6G and case studies for security in AI-based 6G V2X.         4. The starting era of post-quantum cryptography, quantum security, and semantic communications: 6G will mark the starting era of post-quantum cryptography, where traditional encryption methods can no longer withstand the power of quantum computing. To ensure long-term data protection and mitigate the risks of “collect now, decrypt later” attacks, 6G will adopt quantum-safe cryptographic algorithms, such as ML-KEM and HQC, and explore quantum key distribution technologies (e.g., using satellites or aerial systems). In parallel, semantic communication—a paradigm that transmits meaning rather than raw bits—will transform how information is conveyed and protected amid the explosion of data and the limitations of Shannon’s theory. Together, these advancements will redefine digital trust, enhancing network intelligence, security, and resilience for the quantum age.   Provided by: Van-Linh Nguyen

Wavelet Approximation-Aware Residual Network for Single Image Deraining

Wavelet Approximation-Aware Residual Network for Single Image Deraining

May 15, 2025

It has been made great progress on single image deraining based on deep convolutional neural networks (CNN). In most existing deep deraining methods, CNNs aim to learn a direct mapping from rainy images to clean rain-less images, and their architectures are becoming more and more complex. However, due to the limitation of mixing rain with object edges and background, it is difficult to separate rain and object/background, and the edge details of the image cannot be effectively recovered in the reconstruction process. To address this problem, we propose a novel wavelet approximation-aware residual network (WAAR), wherein rain is effectively removed from both low-frequency structures and high-frequency details at each level separately, especially in low-frequency sub-images at each level. After wavelet transform, we propose novel approximation aware (AAM) and approximation level blending (ALB) mechanisms to further aid the low-frequency networks at each level recover the structure and texture of low-frequency sub-images recursively, while the high-frequency network can effectively eliminate rain streaks through block connection and achieve different degrees of edge detail enhancement by adjusting hyperparameters. In addition, we also introduce block connection to enrich the high-frequency details in the high-frequency network, which is favorable for obtaining potential interdependencies between high- and low-frequency features. Experimental results indicate that the proposed WAAR exhibits strong performance in reconstructing clean and rain-free images, recovering real and undistorted texture structures, and enhancing image edges in comparison with the state-of-the-art approaches on synthetic and real image datasets. It shows the effectiveness of our method, especially on image edges and texture details.

Deep-Learning Technique for Bed-exit Action Prediction of Elderly Using Extremely Low-resolution Thermopile Sensor Array

Deep-Learning Technique for Bed-exit Action Prediction of Elderly Using Extremely Low-resolution Thermopile Sensor Array

Mar 01, 2025

Elderly Care is becoming an increasingly important issue in aging and super-aged societies. In particular, Taiwan’s Long-Term Care 3.0 policy highlights “smart assistive technologies” as one of its key areas for promotion. A critical focus in elderly care is fall prevention, as falls in older adults often result in serious or even fatal injuries. Given that bedrooms and bathrooms are the two primary hotspots for falls, this study focuses on the former. The core objective of this research is to prevent falls. However, predicting when a fall will occur is extremely difficult—even in healthy individuals (e.g., someone might trip unexpectedly). Therefore, we considered the typical routines and potential fall causes among elderly individuals and identified a high-risk period during the transition out of bed. During this period, conditions such as orthostatic hypotension or musculoskeletal weakness may lead to momentary dizziness and result in falls. To address this issue, our approach transforms the goal of “fall prevention” into a strategy of “early bed-exit prediction.” By detecting—or even predicting—the elderly person’s intention to get out of bed, our system can alert caregivers, who can then assist verbally (e.g., calling out) or physically, thereby preventing potential falls. To provide caregivers with sufficient response time, this study emphasizes bed-exit prediction rather than simple detection, allowing a buffer of 5–8 seconds for verbal or physical intervention. Currently, smart assistive devices in many care centers rely on air cushions or pressure mats (placed under mattresses) that detect movement only after the person has already gotten out of bed. This is often too late to prevent a fall. Our technology, by contrast, provides an alert during the critical 5–8 second window, significantly improving the chances of fall prevention. Because cameras often raise privacy concerns, our study uses a thermopile-type far-infrared sensor with very low resolution (32×32 pixels). This sensor is inexpensive and inherently privacy-preserving, as the images it produces are unrecognizable to the human eyes. We apply cutting-edge AI and deep learning technologies to predict bed-exit intent on average 5.78 seconds before the actual action. Our database tests show 99.37% accuracy and 99.09% precision. The system supports real-time, online, continuous operation, not just offline database testing, placing it at the forefront of international research. The thermopile sensor used in this study does not present the privacy risks associated with RGB color cameras and is affordably priced between NT$1,500–10,000. However, due to its low resolution (32×32 pixels), traditional image processing and computer vision algorithms perform poorly. To overcome this, we adopted the latest AI and deep learning techniques for practical effectiveness in action prediction. We installed 1–3 far-infrared sensors above the bed (non-intrusive to daily activities) to continuously capture thermal imagery. The data is integrated to anticipate the senior’s intent to get out of bed, allowing caregivers to assist before a fall might occur due to orthostatic hypotension or insufficient leg support. Our system utilizes a combined CNN/LSTM/GRU neural network, along with a custom early-prediction loss function, to accurately predict the senior’s intent to get up—without triggering false alarms caused by minor movements like turning over or lifting a leg during sleep. The results of this research have been showcased at our university’s CIRAS center (Center of Innovative Research for Aging Society) on several occasions, leaving a strong impression on visitors. The findings were also published in 2023 in the IEEE Transactions on Circuits and Systems for Video Technology, an SCI Q1 journal (Ranking: 91.1%) 圖 1 本研究熱電堆紅外線 (TPA) 影像實拍圖 圖 2. 本研究三個紅外線影像感測器 (TPA) 實際配置圖 (床上天花板處) 圖 3. TPA 紅外線影像動作預測系統介面 (左上為三個 TPA 影像,右面為估測之離床機率曲線之時間變化及使用之紅色門檻線(threshold), 當超越門檻線,及發出告警。   Research team:Intelligent Signal Processing, ISP: 520 多媒體實驗室 賴文能老師團隊 (Lie group), Lie group team, R520 laboratory of Intelligent Signal Processing (ISP) group, Department of Electrical Engineering, National Chung Cheng University, Taiwan

1