Fine-tuning Large Language Models (LLMs) for specialized domains is constrained by a fundamental challenge: the need for diverse, cross-organizational data conflicts with the principles of data privacy and sovereignty. While Federated Learning (FL) provides a framework for collaboration without raw data exchange, its classic centralized form introduces a single point of failure and remains vulnerable to model inversion attacks. Decentralized FL (DFL) mitigates this risk by removing the central aggregator but typically relies on inefficient, random peer-to-peer (P2P) pairings, forming a collaboration graph that is blind to agent heterogeneity and risks negative transfer. This paper introduces KNEXA-FL, a novel framework for orchestrated decentralization that resolves this trade-off. KNEXA-FL employs a non-aggregating Central Profiler/Matchmaker (CPM) that formulates P2P collaboration as a contextual bandit problem, using a LinUCB algorithm on abstract agent profiles to learn an optimal matchmaking policy. It orchestrates direct knowledge exchange between heterogeneous, PEFT-based LLM agents via secure distillation, without ever accessing the models themselves. Our comprehensive experiments on a challenging code generation task show that KNEXA-FL yields substantial gains, improving Pass@1 by approximately 50% relative to random P2P collaboration. Critically, our orchestrated approach demonstrates stable convergence, in stark contrast to a powerful centralized distillation baseline which suffers from catastrophic performance collapse. Our work establishes adaptive, learning-based orchestration as a foundational principle for building robust and effective decentralized AI ecosystems.

IP Geolocation has many applications from service tailoring and customization to security, such as fraud detection and location-based access control. Active IP geolocation, where the location of a target is verified by probing, can enhance the trustworthiness of geolocation sufficient for security applications. For example, an NMS, can verify the geographic path a packet takes against a claimed path. Numerous active geolocation solutions have been proposed and developed; however, the vast majority were not designed to mitigate against the reality of potentially malicious probes. We propose a scheme, PARL (Probe-Adversary Resistant Localization), that leverages contradictions in measurements to maintain trust scores of probes that reflect their reliability and are used to eliminate malicious measurements. Unlike the state-of-the-art, PARL does not require the geolocation target to perform probing measurements, making it suitable for general IP geolocation. We evaluate our solution via C++ simulation and demonstrate that given enough iterations, it is able to distinguish between malicious and benign probes in probe networks of up to 44% malicious probes, whereas the state of the art can be tricked into accepting false locations when more than 30% of the probes are malicious. We also demonstrate PARL using the RIPE ATLAS probe network.

Advances in networking and computing are moving society towards a cyber space, in which more aspects of our daily lives are being conducted over the Internet. This movement generates concerns regarding trust between the parties involved in these aspects. Nevertheless, trust is a broad topic and thus it is challenging to define a unified mechanism for evaluating trust in communication networks. This article focuses on presenting a general model of trust in communication networks that is flexible enough to be implemented by a wide range of use cases. The model is based on the concept of trust functions, a type of relationship used to evaluate trust. Trust functions are evaluated between two subjects, based on the action that is about to take place and the objects being affected by that action. We use this model to describe a use case of Trust Enhanced Networking and present a discussion regarding trust in communication networks and future challenges.

Federated learning is a distributed machine learning approach that can be applied to many networking applications. In this paper, we propose a novel blockchain-based secure aggregation protocol for federated learning, which simplifies the existing secure aggregation process by leveraging consensus through blockchain. We demonstrate the prototype by training a general LSTM model for traffic prediction at cell sites based on distributed time series datasets.

In this demo, we demonstrate a novel blockchain based protocol for federated learning. We present the system architecture and describe the blockchain based protocol that seamlessly provides secure communication in federated learning with physically distributed data sets.

A real-world sensing application, which senses and analyzes the situation in the real world via sensor devices, has attracted increasing attention for providing new services to mobile users. In this paper, for targeting the application, we propose a highly adaptive resource control method that can control the amount of local computing resources, which is provided by the Mobile Edge Computing technology and the amount of network resources necessary for service provisioning. A basic idea is to express various information, such as the amount of sensor information and the amount of user access, into a simple potential field, and then update the potential field in a short cycle in a self-organized manner. Numerical results show that our resource control method based on the potential field is adaptive for the movement of users.

We consider virtual optical network (VON) provisioning over a flexible-grid multi-domain optical network with the objective of minimizing total network cost, including the cost of transponders, regenerators, and spectrum. We propose a three-step heuristic algorithm that addresses the issues of domain selection, topology aggregation, and routing, modulation format, and spectrum assignment (RMSA) when mapping virtual optical links onto multi-domain physical optical links. We propose a domain selection technique that attempts to minimize the number of inter- domain virtual optical links. We then suggest a topology aggregation (TA) technique to exchange intra and inter-domain information between domains, and propose a method for RMSA over the aggregated topology. Numerical results show that our heuristic approach is effective in reducing total network cost.

In this paper, we study a new optical network paradigm, where statistical sharing is supported in optical networks. This new paradigm is motivated by the recent revolution of Software Defined Optics (SDO). Software defined variable-bandwidth transponders can support variable data rates for a single connection, i.e. base rates and peak rates. Guaranteeing the peak rates for all the connections simultaneously requires the spectrum for all circuits to be provisioned for peak rates, leading to a large amount of bandwidth usage with low utilization. However, if resources are provisioned for the base rate of each connection, with some shared spectrum resources set aside to allow a fraction of these connections to dynamically switch to their peak rates, then spectrum resources can be allocated more efficiently, allowing a greater number of connections to be accommodated. We reserve a fraction of the spectrum resources for provisioning of base rate of the dynamic traffic while the rest of the spectrum resources are reserved for peak rate, allowing statistical sharing. Our goal is to minimize the blocking of the arriving connection requests, while at the same time maximizing the chance that existing connection requests are able to switch from base rate to peak rate. These two goals conflict with each other; therefore, we need to find a trade-off based on the amount of spectrum resources set aside for the peak rate, and based on the routing, modulation format selection, and spectrum allocation (RMSA) scheme. Our evaluation can help network operators to determine the amount of spectrum that requires to be set aside for peak rates in order to maximize revenue.

In this paper, we consider the problem of routing, modulation, and spectrum assignment (RMSA) for data- flow transfers in elastic optical networks. We design a two-dimensional resource model, in which each data transfer with known data size can be assigned a rectangular block of resources that spans both the spectrum and time dimensions. Furthermore, the dynamic spectral resource allocation problem in elastic optical networks is simplified to the two-dimensional rectangle packing problem. We design a three-tuple for each rectangle placement, and develop a dynamic heuristic algorithm, Best Rectangle Fit (BRF), to efficiently schedule requests while minimizing fragmentation in both spectrum and time domains. We simulate the proposed algorithm, and the results show that the proposed RMSA algorithm (BRF) can greatly decrease blocking probability and increase spectrum utilization.

In this paper, we study a new paradigm in optical networking in which optical spectrum is allowed to be statistically shared between optical circuits, allowing the oversubscription of optical links. We propose a probabilistic model which estimates the capacity requirements for the optical networks under a certain density of statistical sharing. Simulation results indicate that our proposed model can help with network design decisions, such as admission control and capacity and bandwidth allocation in elastic optical networks.

In this paper, we consider the problem of routing, modulation, and spectrum assignment (RMSA) for immediate and advance reservation requests in elastic optical networks. We design a two-dimensional resource model for maintaining resource state information in both spectrum and time domains. For the purpose of minimizing the blocking probability and increasing spectrum utilization, we develop a two phase RMSA algorithm that attempts to decrease spectrum resource fragmentation by scheduling the requests in a manner that takes into account the holding time of each request. We design a simulation to evaluate the performance of the proposed algorithm, and the experiment results show that our proposed two phase RMSA algorithm can greatly reduce blocking probability and obtain high spectrum utilization.

We consider the problem of efficient virtual optical network (VON) mapping in a multi-domain optical network (VON-MD) with the objective of minimizing total network link cost for a given VON demand that is embedded over the multi-domain optical network. Topology aggregation (TA) is used to exchange intra and inter-domain information between domains, and heuristic algorithms are proposed for embedding considering different domain selection techniques and virtual link ordering techniques. We provide an integer linear programming formulation (ILP-VON-MD) to compare with our heuristic approaches. Numerical results show that our heuristic approaches are effective in reducing total network cost.

In this paper, we study the minimum failure resource allocation (MFRA) problem of allocating virtual machines (VMs) across multiple optically interconnected data centers (DCs) with the objective of minimizing the total failure probability based on the information obtained from the optical network virtulization. We first describe the framework of resource allocation, formulate the MFRA problem, and prove that MFRA is NP-complete. We then provide ILP formulation to obtain the optimal solution for small scale problems and two heuristic algorithms, named Minimum SRG Cover (MSC) and Reliable DC Selection (RDS), to solve large scale problems. Numerical results show that both heuristics achieve results close to optimal solutions for small scale problems. Numerical results also show that although RDS has higher time complexity, it outperforms MSC especially when the requested VMs are small.

In this paper, we study the reliable resource allocation (RRA) problem of allocating virtual machines (VMs) from multiple optically interconnected data centers (DCs) with the objective of minimizing the total failure probability based on the information obtained from the optical network virtulization. We first describe the framework of resource allocation, formulate the RRA problem, and prove that RRA is NP-complete. We provide an algorithm, named Minimum Failure Cover (MFC), to obtain optimal solutions for small scale problems. We then provide a greedy algorithm, named VM-over-Reliability (VOR), to solve large scale problems. Numerical results show that VOR achieves results close to optimal solutions gained by MFC for small scale problems. Numerical results also show that VOR outperforms the resource allocation through random DC selection (RDS).

In this paper, we aim to minimize the total network cost in flexible-grid optical networks with multiple line rates. Besides transponder cost, regenerator cost, and shared infrastructure cost, the cost of regenerator sites is also considered. We first provide the problem definition and formulate the problem as an integer linear program (ILP). We also propose a heuristic algorithm considering both selection and placement of equipment to minimize the total network cost. Simulation results show the heuristic algorithm results in up to 28% cost saving, with no significant increase in spectrum usage.

In this paper, we study the problem of regenerator pool site selection for mixed line rate optical networks (MLR-RPSS), with the objective of minimizing the number of regenerator pool sites for a given set of requests. We first provide the problem definition of MLR-RPSS and show that the MLR-RPSS problem is NP-complete. We then present four algorithms, named Independent algorithm, Sequential algorithm, MLR-combined algorithm, and Weighted MLR-combined algorithm. The performance of the algorithms is compared via simulation and results show that the Weighted MLR-combined algorithm has better performance in most cases. Also, when network load is high, the minimum number of regenerator pool sites will approach a certain limit, and some specific nodes will be more likely to be selected as regenerator pool sites.

In this paper, we address the problem of survivable traffic grooming and regenerator placement in optical WDM networks with impairment constraints. The working connections are protected end to end by provisioning bandwidth along a sequence of lightpaths through a dedicated connection-level protection scheme. An auxiliary-graph-based approach is proposed to address the placement of regenerators and grooming equipment for both working and dedicated backup connections in the network with the goal of minimizing the total equipment cost. Simulation results show that the proposed algorithm outperforms a lightpath-level protection algorithm, in which each lightpath is protected separately. We also show the effect of different cost models on equipment placement and evaluate the performance for networks with different line rates.