This paper presents a novel federated learning solution, QHetFed, suitable for Internet of Things deployments, addressing the challenges of clustered geographic distribution, communication resource limitation, and data heterogeneity. QHetFed is based on hierarchical federated learning over multiple device clusters, where the learning process and learning parameters take the necessary data quantization and the data heterogeneity into consideration to achieve high accuracy and fast convergence. Unlike conventional hierarchical federated learning algorithms, the proposed approach combines gradient aggregation in intra-cluster iterations with model aggregation in inter-cluster iterations. We offer a comprehensive analytical framework to evaluate its optimality gap and convergence rate, and give a closed form expression for the optimal learning parameters under a deadline, that accounts for communication and computation times. Our findings reveal that QHetFed consistently achieves high learning accuracy and significantly outperforms other hierarchical algorithms, particularly under heterogeneous data distributions.

In this letter, we depart from the widely-used gradient descent-based hierarchical federated learning (FL) algorithms to develop a novel hierarchical FL framework based on the alternating direction method of multipliers (ADMM), leveraging a network architecture consisting of a single cloud server and multiple edge servers, where each edge server is dedicated to a specific client set. Within this framework, we propose two novel FL algorithms, which both use ADMM in the top layer: one that employs ADMM in the lower layer and another that uses the conventional gradient descent-based approach. The proposed framework enhances privacy, and experiments demonstrate the superiority of the proposed algorithms compared to the conventional algorithms in terms of learning convergence and accuracy. Additionally, gradient descent on the lower layer performs well even if the number of local steps is very limited, while ADMM on both layers lead to better performance otherwise.

In the face of an evolving and increasingly complex threat landscape, organizations must adopt proactive approaches to assess and improve the resilience of their IT infrastructures against potential adversaries. Attack graphs are an effective tool to illustrate adversarial actions, but they often fail to capture the decision-making process of adversaries. To address this limitation, we map MITRE techniques to the attack steps in the attack graph and weight attempt probabilities at decision points according to the threat profile of the attacker. Considering a realistic, large IT infrastructure, we analyze how variations in attacker decision-making impact success rates, path diversity, the most frequent paths, and applied techniques. Our findings show that integrating attacker profiles into threat modeling can support accurate identification of the threat landscape and the optimization of defense strategies.

We consider the problem of non-coherent over-the-air computation (AirComp), where n devices carry highdimensional data vectors x_i ∈ R^d of sparsity ||x_i||₀ ≤ k and the sum of these data vectors has to be computed at a receiver. Previous results on non-coherent AirComp require more than d channel uses to compute functions of x_i, where the extra redundancy is used to combat non-coherent signal aggregation. However, if the data vectors are sparse, sparsity can be exploited to offer significantly cheaper communication. In this paper, we propose to use random transforms to transmit lower-dimensional projections s_i ∈ R^T of the data vectors. These projected vectors are communicated to the receiver using a majority vote (MV)AirComp scheme, which estimates the bit-vector corresponding to the signs of the aggregated projections, i.e., y=sign (Σ_i s_i). By leveraging 1-bit compressed sensing (1bCS) at the receiver, the real-valued and high-dimensional aggregate Σ_i x_i can be recovered from y. We prove analytically that the proposed MVCS scheme estimates the aggregate data vector Σ_ix_i with ℓ₂-norm error ϵ in T=O (k n log (d) / ϵ²) channel uses. We consider distributed histogram estimation, a canonical building block for federated analytics, as an aplication for MVCS where the data vectors x_i are inherently 1 -sparse. Our numerical evaluations demonstrate that our scheme achieves the same order of communication cost as state-of-the-art methods while avoiding the complexity and overhead of additional cryptographic tools.

Motivated by the potential of machine-learning- based (ML) algorithms for radio access network (RAN) control and management, we consider the problem of energy-aware O-RAN service orchestration subject to ML inference time constraints. While ML applications enable complex operations in RAN control, guaranteeing service level agreements to close RAN operations in real time is a key requirement to facilitating their wider adoption. In this paper, we focus on orchestrating ML/AI workloads as near-real-time applications in O-RAN Cloud (O-Cloud). We propose PERX, an energy-efficient and performance-aware O-RAN orchestrator that predicts the performance of diverse sets of colocated ML/AL applications by learning a pairwise characterization of application inference times via hierarchical Bayesian learning. We formulate a latency-constrained integer optimization problem for application orchestration and propose an iterative procedure to solve the problem. In line with industry standards, we adopt Kubernetes as the orchestration framework to develop a latency-aware O-Cloud orchestrator. Experimental results reveal up to 50 % increase in profit with guaranteed service level agreements, compared to state of the art benchmarks.

Cyberinfrastructures are becoming larger and more complex, and it is increasingly challenging to assess for potential attacks and activate the appropriate defences. Attack graphs have been proven as a promising tool for risk assessment, but they also face the challenge of scalability. This paper proposes DefenceRank, an adaptation of Google's PageRank algorithm, to analyze large attack graphs and prioritize defences with low complexity. It incorporates the difficulty of the attack steps through the time-to-compromise parameter, the capabilities of the attack steps and the vulnerability of the assets. The proposed DefenceRank is evaluated on various realistic attack graphs. The results show that it achieves a reasonably high level of accuracy compared to optimal defence selection, while its time complexity increases polynomially with the size of the attack graph and remains in the order of seconds even for very large graphs and a large set of defences. In conclusion, DefenceRank demonstrates a viable alternative for the security assessment of cyberinfrastructures represented by attack graphs.

When implementing hierarchical federated learning over wireless networks, scalability assurance and the ability to handle both interference and device data heterogeneity are crucial. This work introduces a learning method designed to address these challenges, along with a scalable transmission scheme that efficiently uses a single wireless resource through over-the-air computation. To provide resistance against data heterogeneity, we employ gradient aggregations. Meanwhile, the impact of interference is minimized through optimized receiver normalizing factors. For this, we model a multi-cluster wireless network using stochastic geometry, and characterize the mean squared error of the aggregation estimations as a function of the network parameters. We show that despite the interference and the data heterogeneity, the proposed scheme achieves high learning accuracy and can significantly outperform the conventional hierarchical algorithm.

We consider the problem of secure histogram es-timation, where n users hold private items xi from a size-d domain and a server aims to estimate the histogram of the user items. Previous results utilizing orthogonal communication schemes have shown that this problem can be solved securely with a total communication cost of O(n²log(d)) bits by hiding each item xi with a mask. In this paper, we offer a different approach to achieving secure aggregation. Instead of masking the data, our scheme protects individuals by aggregating their messages via a multiple-access channel. A naive communication scheme over the multiple-access channel requires d channel uses, which is generally worse than the O(n²1og(d)) bits communication cost of the prior art in the most relevant regime d >> n. Instead, we propose a new scheme that we call Over-the-Air Group Testing (AirG T) which uses group testing codes to solve the histogram estimation problem in O(n log(d)) channel uses. AirGT reconstructs the histogram exactly with a vanishing probability of error Perror= O(d-^T) that drops exponentially in the number of channel uses T.

When implementing hierarchical federated learning over wireless networks, scalability assurance and the ability to handle both interference and device data heterogeneity are crucial. This work introduces a new two-level learning method designed to address these challenges, along with a scalable over-the-air aggregation scheme for the uplink and a bandwidth-limited broadcast scheme for the downlink that efficiently use a single wireless resource. To provide resistance against data heterogeneity, we employ gradient aggregations. Meanwhile, the impact of uplink and downlink interference is minimized through optimized receiver normalizing factors. We present a comprehensive mathematical approach to derive the convergence bound for the proposed algorithm, applicable to a multi-cluster wireless network encompassing any count of collaborating clusters, and provide special cases and design remarks. As a key step to enable a tractable analysis, we develop a spatial model for the setup by modeling devices as a Poisson cluster process over the edge servers and rigorously quantify uplink and downlink error terms due to the interference. Finally, we show that despite the interference and data heterogeneity, the proposed algorithm not only achieves high learning accuracy for a variety of parameters but also significantly outperforms the conventional hierarchical learning algorithm.

Motivated by the increasing computational capabilities of wireless devices, as well as unprecedented levels of user- and device-generated data, new distributed machine learning (ML) methods have emerged. In the wireless community, Federated Learning (FL) is of particular interest due to its communication efficiency and its ability to deal with the problem of non-IID data. FL training can be accelerated by a wireless communication method called Over-the-Air Computation (AirComp) which harnesses the interference of simultaneous uplink transmissions to efficiently aggregate model updates. However, since AirComp utilizes analog communication, it introduces inevitable estimation errors. In this paper, we study the impact of such estimation errors on the convergence of FL and propose retransmissions as a method to improve FL accuracy over resource-constrained wireless networks. First, we derive the optimal AirComp power control scheme with retransmissions over static channels. Then, we investigate the performance of Over-the-Air FL with retransmissions and find two upper bounds on the FL loss function. Numerical results demonstrate that the power control scheme offers significant reductions in mean squared error. Additionally, we provide simulation results on MNIST classification with a deep neural network that reveals significant improvements in classification accuracy for low-SNR scenarios.