Federated Learning (FL) is a distributed Machine Learning (ML) technique that trains a collaborative ML model without sharing data and by sharing only the model updates. FL is critical in 6 G networks as it enables decentralized and privacy-preserving Artificial Intelligence (AI) model training across distributed devices, reducing communication overhead and enhancing data security, which is crucial for supporting AI-driven 6G networks and applications such as autonomous vehicles, healthcare, and immersive Extended Reality. Since the FL clients transmit only the model updates instead of data, FL is vulnerable to poisoning attacks. The result of a poisoning attack is an incorrect outcome at the inference, affecting the application requirements when employed in 6 G systems. Existing defense mechanisms focus on the attacks in a static nature disregarding the dynamic behavior of attackers. Since the 6 G networks are highly AI-driven, attackers can also learn about the network using AI techniques allowing them to execute more sophisticated dynamic attacks. In this paper, we evaluate how existing defense mechanisms fail in the presence of dynamic poisoning attacks. We also propose novel defense DBFFL against dynamic poisoning attacks in FL, to ensure robustness when deployed in 6 G networks and applications.

The advent of 6th Generation(6G) networks and the rapid expansion of the Internet of Things (IoT) have heightened the security risk potential of such systems to cyberattacks, particularly Denial of Service (DoS) attacks. The 6G networks strongly rely on Artificial Intelligence(AI) for intrusion detection, which yields promising results. In parallel, attackers advance their attacking strategies dynamically, declining the AI-based DoS attack detection accuracy, thereby opening the network for potential attackers flagged as false negatives. This phenomenon, called concept drift, requires dynamic adaptation of the AI-based intrusion detection system using the latest attack data. Explainable AI(XAI) is one of the practical techniques that in-terprets the Machine Learning(ML) model outcome with feature contribution. This paper proposes a novel dynamic adaptation framework for 6G network intrusion detection, integrating real-time monitoring and identifying concept drift from adaptive adversaries using the Wilcoxon stat test. Our work leverages XAI-based feature importance interpretation to optimize required model retraining selectively. This work incorporated Shapley value-based local explanations for selected network traffic samples in the experiment with the UNSW-NB15 attack dataset. We comprehensively evaluated our work with supervised learning techniques for intrusion detection. The results reflect the marginal improvement of DoS classification accuracy by 4.49 % up to 93% in combination with Extreme Gradient Boost(XGB) while marginally reducing training and prediction time by 57.6 % and 47.7% with Gradient Boost(GB) for DoS attack detection beyond state of the art. The results showcase the effectiveness of our work for adaptive adversarial detection in 6G IoT networks with time-efficient dynamic retraining against concept drift with feature selection(19 and 21 out of 42) with improved accuracy.

Federated Learning (FL) is a privacy-preserving distributed Machine Learning (ML) technique. Hierarchical FL is a novel variant of FL applicable to networks with multiple layers. Instead of transmitting client models to the server, hierarchical FL performs aggregations in the layers between the devices and the server. This further reduces the traffic toward the higher layers, which helps efficient link utilization. An adversary can manipulate a set of clients and send malicious model updates toward upper layers to create a trained model with a malicious objective. These attacks, also known as poisoning attacks, disrupt the model training. Like FL, Hierarchical FL is also vulnerable to poisoning attacks since the aggregators do not possess raw data. The existing robust algorithms are designed for FL systems with$n$clients and a server. Therefore, they are not effective against poisoning attacks in hierarchical FL systems. This paper proposes SHIELD, a novel robust aggregation technique that defends hierarchical FL systems from poisoning attacks. We evaluate SHIELD with several datasets in different application areas with different attack strategies and data distributions. The evaluation results demonstrate that SHIELD effectively defends hierarchical FL systems from poisoning attacks with a negligible impact on the benign performance of the models.

Federated Learning (FL) is a distributed Machine Learning (ML) technique that allows model training without sharing data. FL is vulnerable to poisoning attacks where an adversary manipulates the learning process by providing false information to the federation. Ensuring security in FL is vital before using FL in real applications, as the consequences can be adverse. Multi-stage FL is a novel variant of FL that performs intermediate model aggregations, thereby reducing the traffic toward the FL central server. The existing robust aggregation techniques are insufficient in multi-stage FL systems. This paper proposes a novel robust aggregation algorithm against poisoning attacks in a three-layer multi-stage FL system that consists of device, edge, and cloud layers. We evaluate the proposed robust algorithm considering an Augmented Reality (AR) application with different poisoner placements and attack strategies. The evaluation results show that the proposed algorithm can effectively defend against poisoning attacks in three-layer multi-stage FL systems.

Federated learning (FL) has become the next generation of machine learning (ML) by avoiding local data sharing with a central server. While this becomes a major advantage to client-side privacy, it has a trade-off of becoming vulnerable to poisoning attacks and malicious behavior of the central server. As the decentralization of systems enhances security concerns, integrating decentralized defense for the existing FL systems has been extensively studied to eliminate the security issues of FL systems. This paper proposes a decentralized defense approach to FL systems with blockchain technology to overcome the poisoning attack without affecting the existing FL system's performance. We introduce a reliable blockchain-based FL (BCFL) architecture in two different models, namely, Centralized Aggregated BCFL (CA-BCFL) and Fully Decentralized BCFL (FD-BCFL). Both models utilize secure off-chain computations for malicious mitigation as an alternative to high-cost on-chain computations. Our comprehensive analysis shows that the proposed BCFL architectures can defend in a similar manner against poisoning attacks that compromise the aggregator. As a better measure, the paper has included an evaluation of the gas consumption of our two system models.

Network slicing enables the creation of multiple logical independent networks on physical networking infrastructure. Network slice deployment in a Fifth Generation (5G) mobile network can be classified as vertical and horizontal slicing. The paper compares the performance of the two slicing methods through solving two convex optimization problems, considering several smart hospital scenarios that differ from each other based on their medical speciality. The results are used to draw insights on the most appropriate slicing approach for each setup.

The ever growing and revolutionizing demands in telecommunication industry to facilitate numerous business verticals are pushing towards more softwarized mobile communication technologies. Utilizing the capabilities of network softwarization, a novel telecommunication concept of local mobile network has been developed. The local mobile networks are getting popular due to their capability of providing efficient and reliable local services to a focused use case with higher flexibility. This paper presents the practical implementation aspects of a softwarized local mobile network and compare its performance with a conventional mobile network and a hybrid network.

5G calls for a network architecture that ensures ultraresponsive and ultrareliable communication links, in addition to the high degree of flexibility and customization required by different vertical sectors. The novel concept called local 5G networks enables a versatile set of stakeholders to operate 5G networks within their premises with guaranteed quality and reliability to complement mobile network operators' (MNOs) offerings. This article proposes a descriptive architecture for a local 5G operator which provides user specific and location-specific services in a spatially confined environment, i.e., industrial Internet environment. In addition to that, the article proposes hybrid architecture options where both the local 5G operator and MNO collaboratively contribute to establish the core network to cater to such communications. The architecture is discussed in terms of network functions (NFs) and the operational units which entail the core and radio access networks in a smart factory environment which supports Industry 4.0 standards. Moreover, to realize the conceptual design, the article provides simulation results for the latency measurements of the proposed architecture options with respect to an augmented reality (AR), massive wireless sensor networks, and mobile robots use cases. Thereby the article discusses the benefits of deploying core NFs locally to cater to specialized user requirements, rather than continuing with the conventional approach where only MNOs can deploy cellular networks.

In addition to the high degree of flexibility and customization required by different vertical sectors, 5G calls for a network architecture that ensures ultra-responsive and ultra-reliable communication links. The novel concept called micro-operator (uO) enables a versatile set of stakeholders to operate local 5G networks within their premises with a guaranteed quality and reliability to complement mobile network operators' (MNOs) offerings. In this paper, we propose a descriptive architecture for emerging 5G uOs which provides user specific and location specific services in a spatially confined environment. The architecture is discussed in terms of network functions and the operational units which entail the core and radio access networks in a smart factory environment which supports industry 4.0 standards. Moreover, in order to realize the conceptual design, we provide simulation results for the latency measurements of the proposed uO architecture with respect to an augmented reality use case in industrial internet. Thereby we discuss the benefits of having uO driven local 5G networks for specialized user requirements, rather than continuing with the conventional approach where only MNOs can deploy cellular networks.