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).

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.

Current wind energy data platforms face significant challenges in securing and managing extensive data from both offshore and onshore wind farms. These challenges include vulnerabilities to cyber-attacks, data tampering, breaches, complex data-sharing issues due to privacy concerns and regulatory compliance, and a lack of scalability and flexibility in analytical tools for real-time data processing. This paper proposes a novel multilayered data security architecture, termed "VindSec-Llama," to address these challenges. It integrates Generative AI, blockchain, federated learning, and Pipeline Bill of Materials (PBOM) to enhance data analytics, model development, and security across several layers, including Infrastructure, Data Lake, Federated Learning, MLOps, Data Provenance, and LLM. Each layer is designed to meet specific functional requirements, such as handling large datasets, facilitating secure federated learning, automating risk management, and ensuring data provenance and traceability. The platform, deployable in server environments (cloud or on-premises), complies with the Risk Management Framework (RMF) guidelines and security standards. It features a blockchain-enabled, coordinator-less federated learning system to enhance data privacy and security by enabling the development of privacy-preserving machine learning models with data from different wind farms. Automation plays a pivotal role throughout VindSec-Llama, with Meta’s custom-trained Llama-3 LLM used for generating remediation scripts in the Infrastructure Layer and for producing PPBOM in the MLOps Layer. The Llama-3 LLM has been quantized and fine-tuned using Qlora to ensure optimal performance on consumer-grade hardware. The MLOps pipeline setup, a critical functionality of VindSec-Llama, ensures seamless integration and deployment of machine learning models, embodying best practices in continuous integration and delivery. This setup is geared towards maximizing security, compliance, and operational efficiency. A prototype of the platform has been implemented within a wind-energy testbed with the collaboration of Department of Energy US, illustrating its practical applications and benefits.

Large Language Models (LLMs) are widely recognized for their applications in natural language processing tasks, but their potential extends far beyond traditional use cases. This paper introduces "Bassa-Llama," a novel platform that harnesses LLMs for predictive tasks in the realm of network security. Specifically, we propose a platform for real-time network attack detection in Wind Power Plants, leveraging a fine-tuned version of Meta’s Llama-3 LLM alongside blockchain and NFT-based data storage. Using a network PCAP dataset containing both malicious and benign packets, we fine-tune the Llama-3 LLM, with Quantized Low-Rank Adapter (QLoRA), to detect anomalies in network traffic. This approach ensures optimal performance on consumer-grade hardware while significantly enhancing the model’s ability to accurately analyze PCAP data and identify attack patterns. The end-to-end orchestration of the real-time network attack detection flow for Wind Power Plants is fully automated through blockchain smart contracts, and NFTs for storing identified attack data from the PCAP. To the best of our knowledge, this research represents the first effort to utilize a fine-tuned LLM for real-time network attack detection tasks. The results highlight the transformative potential of combining fine-tuned LLMs with blockchain and NFTs to build robust and secure network defense systems for Wind Power Plants. A prototype of the proposed platform was developed in collaboration with the U.S. Department of Energy, utilizing a simulated Wind Power Plant as a testbed.

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.

The main challenges in the 5G/6G network slicing are resource sharing, network slice orchestration, and network optimization in the 5G ecosystem. This paper proposes a novel architecture for a dynamic network slice broker and marketplace named “SliceGPT” that leverages Custom-Trained OpenAI GPT-3.5 LLM, blockchain and NFTs to enable collaboration between different stakeholders in the 5G ecosystem to address these challenges. The platform enables different stakeholders in 5G network slicing (e.g., cloud providers, network operators, RAN providers, and transport network providers) to share and rent their resources to create customized network slices that meet the specific requirements of 5G applications. The orchestration of network slices is managed through blockchain smart contracts, and the resulting network slices are encoded as NFT tokens and made available for purchase in a decentralized NFT marketplace. Customers can select and purchase the network slices that best meet their needs by paying either crypto or flat currency. Revenue generated through the sale of network slices is distributed among different providers, facilitating a fair and efficient marketplace. Intelligent network slice optimization is accomplished through the utilization of a custom-trained GPT-3.5 LLM(which powers the ChatGPT). This LLM can generate valuable insights and recommendations from extensive network datasets, contributing to the optimization of network slices for enhanced performance and efficiency. A prototype of SliceGPT has been implemented with FreedomFi 5G gateway, OpenAirInterface 5G core, OpenAI GPT-3.5-turbo model, LlamaIndex and Langchain. To the best of our knowledge, this is the very first research endeavor to incorporate the GPT LLMs for optimizing 5G/6G network slicing,

Traditional and indigenous medicine, deeply rooted in ancient traditions and wisdom, plays a crucial role in global healthcare and cultural identity. These practices provide treatments for illnesses such as cancer and bone injuries, which often lack effective remedies in Western medicine. However, these valuable systems face challenges like potential knowledge loss, undervaluation of practitioners’ expertise, and the risk of fraud due to the absence of credential verification mechanisms. In this research, we introduce "WedaGPT," a Generative AI-enabled platform that utilizes a custom-trained Meta’s Llama2 Large Language Model (LLM), Blockchain, self-sovereign identity (SSI), Non-Fungible Tokens (NFTs), and model cards to share traditional medical knowledge and address these issues. WedaGPT creates a collaborative ecosystem connecting doctors, medicine providers, therapists, patients, and technology experts, all committed to preserving and advancing traditional healing practices. This platform enables secure and transparent contributions from all stakeholders to patient well-being. Ancient medical recipe books are translated into English and digitized into PDF formats to enrich the platform’s knowledge base. These texts are used to fine-tune the Llama2 LLM, which has been quantized and optimized with Qlora for performance on consumer-grade hardware. Through a chat-based interface in the SSI-enabled mobile wallet, users can interact with the LLM and access detailed information on treatments, recipes, prescriptions, and healing methods. Additionally, users can consult remotely with doctors who prescribe treatments through this wallet. A key feature of WedaGPT is transforming ancient medicinal recipes into NFT tokens for sale on NFT marketplaces, giving traditional knowledge digital authenticity and economic value. Revenue from these sales is distributed among platform contributors, promoting equitable ownership and recognition. Medical recipe data, including treatment histories and physician details, are encapsulated in Model Cards and securely stored on the blockchain. This system offers mechanisms to verify doctors and treatments in a privacy-preserving way, potentially reducing fraud and medication errors.

With the rise of smart vehicles, an intelligent transportation system intelligent transport system (ITS) learning from the tremendous volume of the data generated by the distributed vehicles is becoming a reality. blockchain (BC)-based federated learning (FL) facilities a highly secure and trustless collaborative learning framework; however, it could be inefficient for the time-sensitive services of the Internet of Vehicles (IoV). In this regard, this study investigates information dissemination delay in BC-based FL for IoV using a small world network-based peer selection strategy. Additionally, we also incorporate IoV specific informed decision for peer selection to facilitate even faster dissemination of information in the network and make BC-based system efficient. Network topology of vehicles is represented using a graph approach and based on that the information dissemination delay is formulated. The delay is compared between scenarios when peer selection strategy uses informed decision and that does not use informed decision. The performance of the proposed approach is evaluated through the graph analysis which demonstrates that the inclusion of informed decision reduces the information dissemination delay remarkably.

In recent years, the use of UAVs has expanded to various applications such as surveillance, disaster response, agriculture, and delivery. However, traditional UAV monitoring systems rely on direct communication between the UAV and the ground pilot, which has several limitations such as limited range, poor reliability, and susceptibility to interference. To overcome these limitations, there has been significant interest in integrating UAVs into cellular networks such as 5G/6G network slicing. The flexibility of network slicing allows UAVs to operate on different slices based on their communication needs, which can improve their performance and efficiency. However, integrating UAVs into network slicing also poses several challenges, such as managing communication and permissions of UAVs and base stations, access control of UAVs, and identity management of UAVs. To address these challenges, we propose a blockchain, Non-Fungible Token(NFT), Federated Learning(FL), and Zero-Trust(ZT) security-enabled UAV monitoring platform for 5G/6G network sliced environments. We propose a novel approach in which UAVs are represented as NFT tokens within the platform. This innovative representation allows for enhanced security and trust in the system, aligning with the principles of the Zero-Trust security model, which assumes no implicit trust in any network component or user. Furthermore, we propose a FL system that operates on top of the blockchain, which can analyze data from multiple UAVs across different network slices. Our proposed FL system uses coordinator-less models, which eliminates the attacks of a centralized coordinator. As a use case, we consider a scenario where our proposed system detects anomaly communications of UAVs and identifies attack surfaces via analyzing network traffic data of UAVs using FL. The 5G system testbed implemented with FreedomFi 5G gateway and Indoor Radio Cell.

Federated learning is a collaborative/distributed machine learning system which is designed to address the privacy issues in centralized machine learning systems. The transparency and provenance of a machine learning model are important aspects of federated learning systems since they impact peoples’ lives in various domains (e.g., from healthcare to personal finance to employment). However, most of the existing federated learning systems deal with centralized coordinators which are vulnerable to attacks and privacy breaches. Also, they do not provide any standard transparency and provenance mechanisms for the resulting models. In this paper, we propose a blockchain and Model Card-based integrated federated learning system "Bassa-ML" providing enhanced transparency and trust for the models. Model parameter sharing, local model generation, model averaging, and model sharing functions are implemented using smart contracts. The generated models, model training information, and model reports are stored in the blockchain ledger as Model Card Objects. This results in enhanced transparency and auditability to the federated learning process.

Reinforcement learning (RL) operating on attack graphs leveraging cyber terrain principles are used to develop reward and state associated with determination of surveillance detection routes (SDR). This work extends previous efforts on developing RL methods for path analysis within enterprise networks. This work focuses on building SDR where the routes focus on exploring the network services while trying to evade risk. RL is utilized to support the development of these routes by building a reward mechanism that would help in realization of these paths. The RL algorithm is modified to have a novel warm-up phase which decides in the initial exploration which areas of the network are safe to explore based on the rewards and penalty scale factor.

The proliferation of zero-day threats (ZDTs) to companies’ networks has been immensely costly and requires novel methods to scan traffic for malicious behavior at massive scale. The diverse nature of normal behavior along with the huge landscape of attack types makes deep learning methods an attractive option for their ability to capture highly-nonlinear behavior patterns. In this paper, the authors demonstrate an improvement upon a previously introduced methodology, which used a dual-autoencoder approach to identify ZDTs in network flow telemetry. In addition to the previously-introduced asset-level graph features, which help abstractly represent the role of a host in its network, this new model uses metric learning to train the second autoencoder on labeled attack data. This not only produces stronger performance, but it has the added advantage of improving the interpretability of the model by allowing for multiclass classification in the latent space. This can potentially save human threat hunters time when they investigate predicted ZDTs by showing them which known attack classes were nearby in the latent space. The models presented here are also trained and evaluated with two more datasets, and continue to show promising results even when generalizing to new network topologies.

The network slicing in 5G/6G mobile networks enables billions of connected devices to transmit data at higher rates than ever before. The high number of devices and the huge data rates result in configuration complexities and complex security management. Machine learning techniques could play a key role in managing these system complexities. While feder-ated learning (FL) has recently been proposed as an emerging paradigm to build privacy-preserving machine learning models, many of the existing systems involve centralized coordinators which are known to be vulnerable to attacks and privacy breaches. In addition, current FL models have weak support for transparency and provenance mechanisms. In this paper, we propose a Blockchain-based, Zero-trust Security-enabled Federated Learning system “Skunk” to address privacy and data provenance requirements. The proposed federated learning system also supports the requirements of 5G/6G networks. The sharding-based architecture in the blockchain enables the deployment of Skunk in 5G/6G network slice environments. As a use case of Skunk, we have considered a scenario with IoT device attacks in a 5G/6G network. The proposed FL models detect such attacks in the 5G/6G network sliced environment.

5G network slicing enables IoT networks to connect billions of heterogeneous objects providing high quality of service, high network capacity, and enhanced system throughput. Despite all these advantages, there are some major challenges to be addressed including decentralization, transparency, data interoperability, network privacy and security, and network slice orchestration, data provenance, and management. Blockchain technologies have the potential to offer innovative solutions to overcome these challenges. However, in the context of 5G enabled scalable IoT applications, integrating 5G with blockchain platforms could pose challenges to 5G’s goals such as high transaction throughput, high scalability, and real-time transaction processing, sharding-based consensus, network slice management and provenance. In this paper, "Moose," a blockchain platform, to overcome these challenges is proposed. It supports sharding based consensus in the blockchain network. It integrates a network slice orchestration library with smart contracts to manage and schedule network slices. As a use-case, Moose is integrated with a 5G-supported IoT device identity monitoring system on a network sliced environment. The performance results from the implemented system indicate that the proposed system indeed overcomes the aforementioned challenges.

Anomaly-based machine learning-enabled intrusion detection systems (AML-IDSs) show low performance and prediction accuracy while detecting intrusions in the Internet of Things (IoT) than that of deep learning-based intrusion detection systems (DL-IDSs). In particular, AML-IDS that employ low complexity models for IoT, such as the principal component machine (PCA) method and the one-class support vector machine (1-SVM) method, are inefficient in detecting intrusions when compared to DL-IDS with the two-class neural network (2-NN) method. PCA and 1-SVM AML-IDS suffer from low detection rates compared to DL-IDS. The size of the data set and the number of features or variants in the data set may influence how well PCA and 1-SVM AML-IDS perform compared to DL-IDS. We attribute the low performance and prediction accuracy of the AML-IDS model to an imbalanced data set, a low similarity index between the training data and testing data, and the use of a single-learner model. The intrinsic limitations of the single-learner model have a direct impact on the accuracy of an intelligent IDS. Also, the dissimilarity between testing data and training data leads to an increasingly high rate of false positives (FPs) in AML-IDS than DL-IDS, which have low false alarms and high predictability. In this article, we examine the use of optimization techniques to enhance the performance of single-learner AML-IDS, such as PCA and 1-SVM AML-IDS models for building efficient, scalable, and distributed intelligent IDS for detecting intrusions in IoT. We evaluate these AML-IDS models by tuning hyperparameters and ensemble learning optimization techniques using the Microsoft Azure ML Studio (AMLS) platform and two data sets containing malicious and benign IoT and industrial IoT (IIoT) network traffic. Furthermore, we present a comparative analysis of AML-IDS models for IoT regarding their performance and predictability.

Machine Learning (ML) is on the verge of transitioning from centralized, distributed to federated learning (FL) due to the inherent privacy-preserving framework by FL. FL enables collaborative learning among participants just by exchanging updated model parameters with the FL server while keeping training data local in the end devices which is suitable for vehicular communications. However, this learning framework makes the life of the server difficult to detect the malicious behavior of participants. Malicious model updates from participants may affect the accuracy of the learning model considerably and consequently may cause severe consequences in the Internet of Vehicles (IoV) environment. To address this issue, we propose a novel approach to apply Shiryaev's quickest change detection (QCD) technique in the FL realm. QCD is applied to detect abnormal changes in statistical properties of model parameters in FL as quickly as possible. We apply QCD on the server-side in two ways. First, QCD is applied to detect a change in the statistical properties over the model parameters sent by the participating devices. Second, QCD is applied to the history of aggregated FL model parameters. The first approach facilitates identifying malicious clients which can be eliminated in future learning activities. The other approach assists the server to roll back to an earlier version of the model in case of identifying the anomaly in the aggregated FL parameters. As QCD is applied on the server-side, it does not add any computation overhead on the client-side as well as communication overheard during transmission. These two approaches are evaluated with the help of numerical results.

In the age of sophisticated crimes and terrorism, there is a requirement to develop a perception based multi criteria decision making system that can reveal the hidden clues in the environment of uncertainty. The crime has no fixed dimension to be carried out in. But, still there remain some imprecise clues for the crime site investigation team and precise interpretation of these clues is impossible. That is the place where role of proposed extended fuzzy logic (FLe) comes into play. Moreover, for decision making crime site investigation team has to consider multi criteria with different weights under the uncertainty. So, Extended Fuzzy Logic and Ordered weighted Averaging (OWA) may be taken together as a double folded milestone in revealing the uncertainty in the world of computational forensic. The concept of unprecisiated fuzzy logic (Flu) was introduced by Zadeh. When a perfect solution cannot be given or process falls excessively costly then the role of concept of Flu comes into play. This novel concept provides the basis for FLe. In order to have a better understanding of Flu, the concept of f-geometry is introduced. The proposed work is based on sketching with word technique. We have introduced some f-theorems in proposed work. These f-theorems can be used for estimating the membership value of f-objects in f-geometry. These f-objects may play vital role for identifying clues in computational forensic.

This paper derives a simulation based comparison for UWB-OFDM with different multipath channel models. Several multipath channel models such as (AWGN, Rayleigh and Rician) has been simulated and compared with a proposed hybrid combination of Rayleigh, Rician and AWGN to observe a realistic multipath faded environment. These cases are based on no fading and flat Rayleigh- fading, multiple-diversity reception Rayleigh-fading, and flat Ricean-fading. These simulations are used to determine both signal to noise ratio and bit error rate for multi-amplitude constellations. The combination of Rayleigh and AWGN channels give BER and SNR of 0.5025 and 15.25dB respectively in flat fading mode, whereas combination of Rician and AWGN produces BER and SNR upto 0.4999 and 16.63dB. The proposed Hybrid combination of Rayleigh, Rician and AWGN produces a decay in BER and SNR approximately 2% and 3.5% respectively.