With the rapid proliferation of wireless devices, ensuring secure communication over open wireless channels has become increasingly critical. Physical layer key generation has emerged as a lightweight and information-theoretically secure cryptographic mechanism, offering a promising complement to traditional cryptographic approaches. However, in Internet of Things (IoT) scenarios characterized by heterogeneous devices and highly dynamic environments, conventional physical-layer key generation methods suffer from low key generation rates, poor stability, and limited adaptability. To address these challenges, this paper proposes a novel AI-based physical layer key generation framework that integrates multi-source signal fusion and intelligent feature selection. Specifically, deep learning models are employed to fuse features from multiple heterogeneous wireless signal sources, enabling the extraction of high-quality randomness and enhancing key entropy and security. In parallel, an attention mechanism is employed to dynamically select the most suitable physical layer features based on real-time environmental conditions, thereby enhancing the system’s adaptability and robustness in complex IoT settings. Finally, we outline potential future research directions and discuss the feasibility of implementing the proposed framework in real-world deployments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

Federated Learning (FL) enables collaborative model training without sharing raw data, but remains vulnerable to poisoning attacks from malicious clients. Existing defenses are often reactive and require costly model retraining, making them inefficient and impractical for real-time protection. We propose FedCleaner, a server-side dual-mechanism framework that combines: Proactive Layer-Wise Anomaly Detection to identify poisoned updates in real time; Retroactive Contribution Erasure to efficiently unlearn malicious client influences without retraining. Experiments on datasets show that FedCleaner provides a scalable, privacy-preserving, and regulation-compliant solution to defend FL systems against persistent poisoning threats. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

With the rapid proliferation of mobile sensing in fields such as personal health monitoring in data processing are becoming more prominent. This paper introduces a decentralized DETR framework inspired by blockchain proof-of-work consensus. The framework trains models locally on each device and evaluates the device's reputation based on its historical performance. Only devices meeting predefined criteria are admitted to the update committee, which enhances security. This mechanism reduces reliance on centralized servers and minimizes infrastructure costs. While a supervisory operator ensures the smooth operation of the system. To further enhance trust, we propose a credibility assessment method that integrates risk metrics with data quality scores via a non-cooperative game-theoretic model. By achieving Nash equilibrium, this method not only guarantees local optimality but also prioritizes users who provide high-quality, low-risk data, thereby promoting timely committee updates to achieve global optimality. As a complement to DETR, we propose BAL-IDS, an advanced intrusion detection system (IDS) that extracts latent features using autoencoders and dynamically fine-tunes the hyperparameters of OCSVM using a Bayesian joint local agent optimization strategy. This dual approach enhances the system's resilience to complex threats, especially those that exploit requester feedback mechanisms. Experiments show that our research is superior to traditional schemes. © 2025 Elsevier B.V.

Tool-using LLM agents for health monitoring raise critical privacy concerns as they share sensitive patient data with cloud providers and third-party models. This study presents HealthAgent, a privacy-preserving LLM agent framework that protects both user queries and multi-modal sensor data through homomorphic encryption. HealthAgent enables an LLM orchestrator to coordinate specialized AI models for complex health assessments while processing all data in encrypted form. The system achieves 95% task decomposition accuracy with 10s latency, demonstrating that strong privacy guarantees can be maintained without sacrificing real-time performance in health monitoring applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

Large Language Models (LLMs) are increasingly used to generate dynamic dialogue for game NPCs. However, their integration raises new security concerns. In this study, we examine whether adversarial prompt injection can cause LLM-based NPCs to reveal hidden background secrets that are meant to remain undisclosed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

Federated Learning (FL) enables privacy-preserving model training across distributed clients. However, its reliance on voluntary client participation makes it vulnerable to strategic behaviors—actions that are not overtly malicious but significantly impair model convergence and fairness. Existing defense methods primarily focus on explicit attacks, overlooking the challenges posed by economically motivated "pseudo-honest" clients. To address this gap, we propose a Reputation-Aware Defense Framework to mitigate strategic behaviors in FL. This framework introduces a multi-dimensional dynamic reputation model that evaluates client behaviors based on gradient alignment, participation consistency, and update stability. The resulting reputation scores are incorporated into both aggregation and incentive mechanisms, forming a behavior-feedback loop that rewards honest participation and penalizes opportunistic strategies. We theoretically prove the convergence of reputation scores, the suppression of low-quality updates in aggregation, and the emergence of honest participation as a Nash equilibrium under the incentive mechanism. Experiments on datasets such as CIFAR-10, FEMNIST, MIMIC-III demonstrate that our approach significantly outperforms baseline methods in accuracy, fairness, and robustness, even when up to 60% of clients act strategically. This study bridges trust modeling and robust optimization in FL, offering a secure foundation for federated systems operating in open and incentive-driven environments. © 2025 by the authors.

The Internet of Things (IoT) connects physical devices to the Internet via open communication protocols. Malicious actors can exploit vulnerabilities to steal data or manipulate critical IoT settings, so there is a need for strong security measures. We propose an improved real-time intrusion detection system (IDS) called the real-time credibility system (RTCS), which utilizes traffic statistics and authentication analysis to compute credibility. RTCS performs the authentication process by utilizing elliptic curve encryption and decryption operations, basic symmetric encryption, and hash functions. This process enables anonymous mutual authentication between IoT devices. Subsequently, RTCS accesses sparsified user history data and introduces flexibility in calculating user credibility by employing an adapted secondary paradigm combined with preset "tolerance parameters," which serve as optimal thresholds for classifying different users. When a normal user violates regulations, their credibility decreases by a specified degree. If a high-risk user commits another violation, RTCS cannot tolerate it, leading to a rapid decline in their credibility. RTCS implements diversion measures and provides assisted decision scores for different users. Experimental results demonstrate that our method achieves an F1-score of 0.9707 and an area under the curve score of 0.9535. Compared to other works, RTCS exhibits superior performance and proactivity.

The rapid development of consumer electronics technology has greatly promoted the progress of the metaverse. However, as a digitized virtual environment, the metaverse imposes high demands on the security of user identities and assets. In this context, asynchronous remote distributed key generation has become one of the key technologies to ensure the security of the metaverse. Unlike traditional key generation methods, the asynchronous nature makes the distributed key generation process more flexible, helping to address the dynamic and heterogeneous network environment within the metaverse. This paper proposes an asynchronous remote key generation method. This method employs public-key cryptography and basic asynchronous primitives to accomplish remote key generation and exchange through encryption and decryption operations between different nodes. In comparison to traditional methods, the asynchronous remote key generation approach provides higher security and reliability, while also showcasing increased efficiency and flexibility. IEEE

Federated learning (FL) has become an essential enabler of distributed intelligence in cyber-physical-social systems (CPSSs), facilitating decentralized collaboration while upholding data privacy. As CPSS applications increasingly rely on federated models for tasks such as predictive analytics and decision-making, safeguarding the intellectual property of these models has emerged as a pressing concern. To address this, we propose MarkFL, an efficient and easy-to-implement watermarking approach tailored for federated models in CPSS environments. MarkFL enables clients to locally train their models on original tasks while the server simultaneously trains its model on a watermark set. During the weighted averaging phase, a new global model embedded with the watermark is generated. This approach ensures no additional time overhead and offers precise control over its impact on the primary tasks, making MarkFL both efficient and practical for diverse applications. Through experiments on the CIFAR-10 dataset, we demonstrate that MarkFL seamlessly integrates into the FL process while maintaining resilience against watermark removal attacks. To further optimize its performance, we introduced a watermark set generated using minimal training samples, showcasing its potential as a robust and practical solution for real-world FL scenarios.

Federated learning has rapidly advanced as a privacy-preserving, distributed machine learning methodology. Protecting the intellectual property rights of federated models, however, poses significant challenges. Existing backdoor-based watermarking techniques suffer from complexity, inefficiency, and implementation challenges. In this paper, we present AggreMark, a novel watermarking approach that incorporates parallel server-side training and watermark embedding during the weighted averaging phase of federated learning. This method does not alter the original model structure or parameters related to the original learning task and adds no additional time overhead, ensuring its practicality for real-world applications. AggreMark is easy to implement and maintain, and it robustly preserves the model's high performance. We validate the method's effectiveness and robustness against pruning-based watermark removal attacks through experiments on CIFAR-10. © 2024 IEEE.