Accurate waveform identification, especially at low SNRs, remains an open challenge; both classical hypothesis-test detectors and modern deep neural networks degrade sharply as SNR falls. We address this with a graph-neural approach that converts each noisy in-phase/quadrature (IQ) segment into a multi-scale temporal graph: every sample becomes a node linked to neighbors at multiple lags (±1,±2,±4,±8) and to feature-space k-nearest neighbors. Each node carries a six-channel feature vector $\left[ {I,Q,|x|,\phi ,\delta \phi ,|x{|^2}} \right]$ designed to surface subtle patterns masked by noise. A hybrid CNN-GNN then performs classification: a 1D convolutional front-end learns local temporal embeddings, followed by a deep residual GNN with interleaved GCN and GATv2 layers to propagate information over the graph. We use Jumping Knowledge (JK) aggregation to preserve multi-hop and shallow cues, and an attention-based readout to emphasize the most informative nodes. On a synthetic four-class dataset (LTE, 5G NR, Radar, noise) at −10dB average SNR, the proposed model attains 91.3% test accuracy, exceeding strong baselines. This demonstrates substantial performance gains over conventional CNNs and deep learning classifiers in the low-SNR regime.

Modern 5G networks offer a network-sliced infrastructure where each network slice contains a dedicated 5G core software service layer. The 5G core software services in each slice shares common core network resources to meet specific customer needs. A primary challenge in 5G network slicing involves resource sharing and efficient network slice orchestration. Container-based methodologies, including tools like Docker and Kubernetes, have become popular for orchestrating 5G network slice services and managing configurations in microservices-based cloud-native service deployment. However, despite their utility, these tools present significant challenges. Their complexity often necessitates dedicated DevOps teams for effective management, while configuration management can prove arduous, and end-to-end supply chain oversight is lacking. To address these challenges, this paper introduces “Llama-Recipe,” a cloud-native 5G-core service deployment and orchestration platform integrating Generative AI, SBOM, PBOM and NFT. 5G-core service configurations across different network slices are represented as “HOCON (Human-Optimized Config Object Notation)” config objects adhering to the GitOps paradigm. Leveraging custom-trained Meta's Llama2 LLM, Llama-Recipe generates the Kubernetes manifests for network-sliced 5G-core services based on the defined HOCON configurations. The generated Kubernetes manifests of the 5G-core services are deployed in designated Kubernetes clusters utilizing GitOps tools (e.g., ArgoCD), ensuring seamless and automated deployment processes. Additionally, Llama-Recipe introduced a novel mechanism to handle end-to-end supply chain verification of 5G-core software services using Software-Bill of Materials (SBOM) and Pipeline-Bill of Materials (PBOM). SBOMs track all the dependencies and PBOMs facilitate the comprehensive tracking of end-to-end supply chain data for 5G-core software services, enhancing transparency and security. These PBOMs are also generated using the fine-tuned Meta's Llama-2 LLM and are encoded as NFT tokens with a novel NFT token schema. This schema enables easy verification and validation of supply-chain data during deployments, thus helping to prevent various supply-chain attacks. To fine-tune the Meta's Llama2 LLM, we've undertaken a meticulous training process, collaborating with Qlora to transform a 4-bit quantized pre-trained language model into Low-Rank Adapters(LoRA). The effectiveness of the Llama-Recipe is demonstrated through a real-world test-bed deployment in a sliced network scenario, utilizing multiple 5G cores (i.e., Open5GS) across Ericsson's new Radio Access Network (RAN).

Emerging sixth-generation (6G) edge networks demand intelligent, scalable, and privacy-preserving learning systems that support real-time decision-making and natural language-driven control. In addition to training, these systems must also support federated unlearning (FU), the ability to selectively remove user data without full model retraining. However, existing federated learning (FL) and FU frameworks lack adaptability, require manual hyperparameter tuning, and are ill-suited for dynamic, resource-constrained environments. To address these challenges, we propose SLM-FARL, a hierarchical multi-agent deep reinforcement learning (MARL) framework that integrates small language models (SLMs) with FL and FU processes for autonomous, privacy-compliant learning aligned with user-level data removal demands. We implement a customized MAPPO algorithm to enable stable and adaptive policy updates across distributed SLM agents, orchestrated by a central LLM controller that supports human-in-the-loop interaction. To ensure real-time responsiveness and deployment efficiency, we incorporate SLM optimization techniques such as quantization and knowledge distillation, reducing model size and latency while maintaining performance. The proposed framework is evaluated on the UCI Adult dataset using 120 clients and demonstrates up to 15.78% higher FL-FU accuracy compared to baseline methods. The MAPPO Loss decreased by 90.12% indicates highly effective MARL convergence and Policy Entropy drop by 84.31% shows it confident policy decisions. The KD demonstrated an overall 17.56% improved performance over other model compression techniques. Thus, these metrics affirms the robustness and adapt-ability of our proposed SLM-FARL framework.

Transfer learning, a method that influences pretrained models to improve performance on new tasks, faces several data privacy, security, and scalability challenges when applied in decentralized environments. Recently, there have been few attempts to integrate blockchain technology with a transfer-learning approach. However, these classical blockchainbased non-collaborative transfer learning models face significant challenges, including poor scalability, security vulnerability, lack of data diversity, and inefficient incentive structures, thereby hindering the effectiveness and efficiency of the transfer learning process. This paper presents a unified framework that utilizes decentralized blockchain technology for collaborative transfer learning. The framework enables secure model sharing within a collaborative learning environment, supported by incentive mechanisms while maintaining model integrity and providing context protection. We perform extensive experimental studies with eight well-known large-scale and fine-grained image datasets. After initial transfer learning, incorporating collaborative learning via the decentralized blockchain network yielded promising results. The global model, after aggregating contributions from all entities, shows an impressive 6.8 % to 10.0 % accuracy improvement compared to individual baseline models. For blockchain implementation, we use the Rahasak blockchain as the ledger and its Aplos platform for a customized smart contract interface. Rahasak-CA, the certificate authority of the Rahasak blockchain, stores the digital certificates of peers in the transfer learning process. The system was deployed using Docker and Kubernetes, and evaluated on the proposed testbed.

Federated Learning (FL) is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property (IP) threats. Model extraction (ME) attack poses a significant risk to Machine-Learning-as-a-Service (MLaaS) platforms, enabling attackers to replicate confidential models by querying Black-Box (without internal insight) APIs. Despite FL’s privacy-preserving goals, its distributed nature makes it particularly susceptible to such attacks. This paper examines the vulnerability of the FL-based victim model to two types of model extraction attacks. For various federated clients built under NVFlare platform, we implemented ME attack across two deep-learning architectures and three image datasets. We evaluate the proposed ME attack performance using various metrics, including accuracy, fidelity, and KL divergence. The experiments show that for various FL clients, the accuracy and fidelity of the extraction model are closely related to the size of the attack query set. Additionally, we explore a transfer learning-based approach where pre-trained models serve as the starting point for the extraction process. The results indicate that the accuracy and fidelity of the fine-tuned pre-trained extraction models are notably higher, particularly with smaller query sets, highlighting potential advantages for attackers.

Internet of Things (IoT) platforms with trigger-action capability allow event conditions to trigger actions in IoT devices autonomously by creating a chain of interactions. Adversaries exploit this chain of interactions to maliciously inject fake event conditions into IoT hubs, triggering unauthorized actions on target IoT devices to implement remote injection attacks. Existing defense mechanisms focus mainly on the verification of event transactions using physical event fingerprints to enforce security policies to block unsafe event transactions. These approaches are designed to provide offline defense against injection attacks. The state-of-the-art online defense mechanisms offer real-time defense, but extensive dependency on the inference of attack impacts on the IoT network limits the generalization capability of these approaches. In this paper, we propose a platform-independent multi-agent online defense system, namely RESTRAIN, to counter remote injection attacks at runtime. RESTRAIN allows the defense agent to profile attack actions at runtime and leverages reinforcement learning to optimize a defense policy that complies with the security requirements of the IoT network. The experimental results show that the defense agent effectively takes real-time defense actions against complex and dynamic remote injection attacks and maximizes the security gain with minimal computational overhead.

The convergence of diverse wireless technologies inside a unified e-healthcare platform has opened up several vulnerabilities to cyber threats. To assure data integrity and reduce system overhead, aggregate signature methods provide a convenient way to combine multiple message signatures into a single compact signature. However, classical aggregate signature schemes are vulnerable to quantum threats and device impersonation attacks. To mitigate the research gap, in this paper, we leverage the benefits of Physical Unclonable Function (PUF) and public blockchain to propose a quantum-safe latticebased aggregate signature scheme (P2Q-ABS). The security of P2Q-ASB is based on the difficulty of the Ring Learning-withError (Ring-LWE) problem. The proposed P2Q-ASB scheme is a unified approach that protects IoMT devices with PUFs, provides quantum-resistant aggregate signatures, and stores electronic medical records in a blockchain-based distributed ledger. We provide a testbed implementation of lattice-based signatures for single and group messages. Moreover, we show the blockchain simulation results for various blocks mined and transactions per block. Security and performance analysis shows that P2Q-ASB offers enhanced security measures and facilitates more efficiency when compared to current state-of-the-art methodologies.

Machine Learning as a Service (MLaaS) enables users to leverage powerful machine learning models through cloud-based APIs, offering scalability and ease of deployment. However, these services are vulnerable to model extraction attacks, where adversaries repeatedly query the application programming interface (API) to reconstruct a functionally similar model, compromising intellectual property and security. Despite various defense strategies being proposed, many suffer from high computational costs, limited adaptability to evolving attack techniques, and a reduction in performance for legitimate users. In this paper, we introduce a Resilient Adaptive Defense Framework for Model Extraction Attack Protection (RADEP), a multifaceted defense framework designed to counteract model extraction attacks through a multi-layered security approach. RADEP employs progressive adversarial training to enhance model resilience against extraction attempts. Malicious query detection is achieved through a combination of uncertainty quantification and behavioral pattern analysis, effectively identifying adversarial queries. Furthermore, we develop an adaptive response mechanism that dynamically modifies query outputs based on their suspicion scores, reducing the utility of stolen models. Finally, ownership verification is enforced through embedded watermarking and backdoor triggers, enabling reliable identification of unauthorized model use. Experimental evaluations demonstrate that RADEP significantly reduces extraction success rates while maintaining high detection accuracy with minimal impact on legitimate queries. Extensive experiments show that RADEP effectively defends against model extraction attacks and remains resilient even against adaptive adversaries, making it a reliable security framework for MLaaS models.

Low-power wireless sensor networks (WSNs) and Internet of Things (IoT) have great impact for the real-time applications in future 5th generation (5G) mobile networks due to the wireless-powered communication technologies. The Age of Information (AoI) plays a crucial performance metric in an IoT-enabled real-time smart warehouse application, where the freshness of the aggregated data is very important. However, wireless medium communication among the beacon nodes and the user equipments (tracking nodes) gives an opportunity to an adversary not only to eavesdrop the data but also to corrupt the data by means of deleting, modifying or inserting malicious information during communication among the entities involved in the smart warehouse environment. To mitigate these issues, we design a security scheme for AoI-enabled 5G smart warehouse through an access control mechanism, where the secure communication among the beacon nodes and the tracking nodes will take place by mutual device authentication and key agreement process. The fresh data collected at the enterprise cloud is then used for big data analytics for better predictions and analysis, such as optimal device scheduling so that the data becomes very fresh. The rigorous security analysis and comparative study show that the proposed mechanism has significantly better security and comparable communication and computational costs as compared to the relevant schemes. In addition, through the real-time testbed experiments, we show that the proposed scheme is practical in 5G smart warehouse context.

Mobile cloud computing (MCC) allows mobile users to have on-demand access to cloud services. A mobile cloud model helps in analyzing the information regarding the patients' records and also in extracting recommendations in healthcare applications. In MCC, a fine-grained level access control of multiserver cloud data is a prerequisite for successful execution of end-users applications. In this paper, we propose a new scheme that provides a combined approach of fine-grained access control over cloud-based multiserver data along with a provably secure mobile user authentication mechanism for the Healthcare Industry 4.0. To the best of our knowledge, the proposed scheme is the first to pursue fine-grained data access control over multiple cloud servers in a MCC environment. The proposed scheme has been validated extensively in different heterogeneous environment where its performance was found good in comparison to other existing schemes.

The recent proliferation of mobile devices, such as smartphones and wearable devices has given rise to crowdsourcing Internet of Things (IoT) applications. E-healthcare service is one of the important services for the crowdsourcing IoT applications that facilitates remote access or storage of medical server data to the authorized users (for example, doctors, patients, and nurses) via wireless communication. As wireless communication is susceptible to various kinds of threats and attacks, remote user authentication is highly essential for a hazard-free use of these services. In this paper, we aim to propose a new secure three-factor user remote user authentication protocol based on the extended chaotic maps. The three factors involved in the proposed scheme are: 1) smart card; 2) password; and 3) personal biometrics. As the proposed scheme avoids computationally expensive elliptic curve point multiplication or modular exponentiation operation, it is lightweight and efficient. The formal security verification using the widely-accepted verification tool, called the ProVerif 1.93, shows that the presented scheme is secure. In addition, we present the formal security analysis using the both widely accepted real-or-random model and Burrows-Abadi-Needham logic. With the combination of high security and appreciably low communication and computational overheads, our scheme is very much practical for battery limited devices for the healthcare applications as compared to other existing related schemes.

Multi-server environment is the most common scenario for a large number of enterprise class applications. In this environment, user registration at each server is not recommended. Using multi-server authentication architecture, user can manage authentication to various servers using single identity and password. We introduce a new authentication scheme for multi-server environments using Chebyshev chaotic map. In our scheme, we use the Chebyshev chaotic map and biometric verification along with password verification for authorization and access to various application servers. The proposed scheme is light-weight compared to other related schemes. We only use the Chebyshev chaotic map, cryptographic hash function and symmetric key encryption-decryption in the proposed scheme. Our scheme provides strong authentication, and also supports biometrics & password change phase by a legitimate user at any time locally, and dynamic server addition phase. We perform the formal security verification using the broadly-accepted Automated Validation of Internet Security Protocols and Applications (AVISPA) tool to show that the presented scheme is secure. In addition, we use the formal security analysis using the Burrows-Abadi-Needham (BAN) logic along with random oracle models and prove that our scheme is secure against different known attacks. High security and significantly low computation and communication costs make our scheme is very suitable for multi-server environments as compared to other existing related schemes.