The application of message-passing Graph Neural Networks has been a breakthrough for important network science problems. However, the competitive performance often relies on using handcrafted structural features as inputs, which increases computational cost and introduces bias into the otherwise purely data-driven network representations. Here, we eliminate the need for handcrafted features by introducing an attention mechanism and utilizing message-iteration profiles, in addition to an effective algorithmic approach to generate a structurally diverse training set of small synthetic networks. Thereby, we build an expressive message-passing framework and use it to efficiently solve the NP-hard problem of Network Dismantling, virtually equivalent to vital node identification, with significant real-world applications. Trained solely on diversified synthetic networks, our proposed model—MIND: Message Iteration Network Dismantler—generalizes to large, unseen real networks with millions of nodes, outperforming state-of-the-art network dismantling methods. Increased efficiency and generalizability of the proposed model can be leveraged beyond dismantling in a range of complex network problems.

Ocean data collection, instrumental for addressing global issues such as climate change and biodiversity conservation, relies on IoT devices deployed on marine vessels. Despite their significance, traditional blockchain-based data collection systems have scalability and energy efficiency limitations. Moreover, ensuring the secure journey of data from its origin to a remote storage location is a critical concern often overlooked. This paper presents a system design fortified with a novel secure batch data-assisted IOTA scheme, enhancing the efficiency and security of data collection while reducing the computational load on small IoT devices. The proposed system is based on three core components: 1) lightweight cryptography, employing Hash-based Message Authentication Codes (HMAC) and Elliptic Curve Integrated Encryption Scheme (ECIES), chosen for their scalability and suitability for low-power IoT devices; 2) batch data aggregation, introduced in IOTA to augment throughput and reduce latency by processing large data volumes concurrently; and 3) secure and scalable data storage using the recent version of IOTA, namely Chrysalis. Rigorous testing on small IoT devices substantiates the acceptable performance of the system in terms of computation overhead compared to existing systems. By integrating IOTA Chrysalis, hybrid cryptography, and the batch data concept, this method offers an efficient, secure solution for large-scale ocean data collection.

Interpretability is crucial for ensuring RL systems align with human values. However, it remains challenging to achieve in complex decision making domains. Existing methods frequently attempt interpretability at the level of fundamental model units, such as neurons or decision nodes: an approach which scales poorly to large models. Here, we instead propose an approach to interpretability at the level of functional modularity. We show how encouraging sparsity and locality in network weights leads to the emergence of functional modules in RL policy networks. To detect these modules, we develop an extended Louvain algorithm which uses a novel `correlation alignment' metric to overcome the limitations of standard network analysis techniques when applied to neural network architectures. Applying these methods to 2D and 3D MiniGrid environments reveals the consistent emergence of distinct navigational modules for different axes, and we further demonstrate how these functions can be validated through direct interventions on network weights prior to inference.

We describe an architecture for a decentralised data market for applications in which agents are incentivised to collaborate to crowd-source their data. The architecture is designed to reward data that furthers the market's collective goal, and distributes reward fairly to all those that contribute with their data. We show that the architecture is resilient to Sybil , wormhole , and data poisoning attacks. In order to evaluate the resilience of the architecture, we characterise its breakdown points for various adversarial threat models in an automotive use case.

A growing issue across multiple fields involves verifying that an individual or object is truly in the location it claims to be and, despite the significance of this problem, the scientific community has not extensively explored how to provide proof for such claims. Accordingly, this article presents a novel class of proof-of-position algorithms: tree-proof-of-position (T-PoP). These algorithms are decentralized, collaborative and can be computed in a privacy preserving manner, such that agents do not need to reveal their position publicly. We make no assumptions of honest behavior in the system, and consider varying ways in which agents may misbehave. T-PoP is therefore resilient to adversarial scenarios, which makes it suitable for a wide class of applications, namely those where trust in a centralized infrastructure may not be assumed, or high security risk scenarios. Our algorithm has a worst case quadratic runtime, making it suitable for hardware constrained IoT applications. We also provide a mathematical model that summarizes T-PoP’s performance for varying operating conditions. Using a large number of agent-based simulations, we verify the agreement between TPoP’s performance and our mathematical predictions. T-PoP can achieve high levels of reliability and security by tuning its operating conditions, both in high and low density environments. Finally, we also present a mathematical model to probabilistically detect platooning attacks.

Reinforcement Learning (RL) is a powerful method for controlling dynamic systems, but its learning mechanism can lead to unpredictable actions that undermine the safety of critical systems. Here, we propose RL with Adaptive Regularization (RL-AR), an algorithm that enables safe RL exploration by combining the RL policy with a policy regularizer that hard-codes the safety constraints. RL-AR performs policy combination via a "focus module," which determines the appropriate combination depending on the state—relying more on the safe policy regularizer for less-exploited states while allowing unbiased convergence for well-exploited states. In a series of critical control applications, we demonstrate that RL-AR not only ensures safety during training but also achieves a return competitive with the standards of model-free RL that disregards safety.

This article describes the use of acrlong DLTs as a means to create personalized social nudges and to influence the behavior of agents in a smart city environment. Specifically, we present a scheme to price personalized risk in sharing economy applications. We provide proofs for the convergence of the proposed stochastic system and we validate our approach through the use of extensive Monte Carlo simulations.

In the Internet of Things (IoT) domain, devices need a platform to transact seamlessly without a trusted intermediary. Although distributed ledger technologies (DLTs) could provide such a platform, blockchains, such as Bitcoin, were not designed with IoT networks in mind, hence are often unsuitable for such applications: they offer poor transaction throughput and confirmation times, put stress on constrained computing and storage resources, and require high transaction fees. In this article, we consider a class of IoT-friendly DLTs based on directed acyclic graphs, rather than a blockchain, and with a reputation system in the place of Proof of Work (PoW). However, without PoW, the implementation of these DLTs requires an access control algorithm to manage the rate at which nodes can add new transactions to the ledger. We model the access control problem and present an algorithm that is fair, efficient, and secure. Our algorithm represents a new design paradigm for DLTs in which concepts from networking are applied to the DLT setting for the first time. For example, our algorithm uses distributed rate setting, which is similar in nature to transmission control used in the Internet. However, our solution features novel adaptations to cope with the adversarial environment of DLTs in which no individual agent can be trusted. Our algorithm guarantees utilization of resources, consistency, fairness, and resilience against attackers. All of these are achieved efficiently and with regard for the limitations of IoT devices. We perform extensive simulations to validate these claims.

Access control is a fundamental component of the design of distributed ledgers, influencing many aspects of their functionality, such as fairness, efficiency, traditional notions of network security, and adversarial attacks such as Denial-of-Service (DoS) attacks.1In this work, we consider the security of a recently proposed access control protocol for directed acyclic graph-based distributed ledgers. We present a number of attack scenarios and potential vulnerabilities of the protocol and introduce a number of additional features which enhance its resilience. Specifically, a blacklisting algorithm, which is based on a reputation-weighted threshold, is introduced to handle both spamming and multirate malicious attackers. A solidification request component is also introduced to ensure the fairness and consistency of the network in the presence of attacks. Finally, a timestamp component is also introduced to maintain the consistency of the network in the presence of multirate attackers. Simulations to illustrate the efficacy and robustness of the revised protocol are also presented.

We introduce a permissioned distributed ledger technology (DLT) design for crowdsourced smart mobility applications. This architecture is based on a directed acyclic graph architecture (similar to the IOTA tangle) and uses both Proof-of-Work and Proof-of-Position mechanisms to provide protection against spam attacks and malevolent actors. In addition to enabling individuals to retain ownership of their data and to monetize it, the architecture is also suitable for distributed privacy-preserving machine learning algorithms, is lightweight, and can be implemented in simple internet-of-things (IoT) devices. To demonstrate its efficacy, we apply this framework to reinforcement learning settings where a third party is interested in acquiring information from agents. In particular, one may be interested in sampling an unknown vehicular traffic flow in a city, using a DLT-type architecture and without perturbing the density, with the idea of realizing a set of virtual tokens as surrogates of real vehicles to explore geographical areas of interest. These tokens, whose authenticated position determines write access to the ledger, are thus used to emulate the probing actions of commanded (real) vehicles on a given planned route by “jumping” from a passing-by vehicle to another to complete the planned trajectory. Consequently, the environment stays unaffected (i.e., the autonomy of participating vehicles is not influenced by the algorithm), regardless of the number of emitted tokens. The design of such a DLT architecture is presented, and numerical results from large-scale simulations are provided to validate the proposed approach.

In this article, we propose a stochastic decentralized algorithm to recommend the most convenient charging station (CS) to plug-in electric vehicles (PEVs) that need charging. In particular, we use different cost functions to describe the possibly different priorities of PEV drivers, such as the preference to minimize charging costs, charging times, or the distance between them and the CS. For this purpose, we leverage on an Internet of Things architecture based on a permissioned distributed ledger technology (DLT) to enforce compliance of drivers and reduces the occurrence of detrimental misbehaviors of drivers. Extensive simulations performed with the mobility simulator SUMO in realistic city-wide networks have been provided to illustrate how the proposed PEV assignment procedure works in practice, and to validate its performance.

COVID-19 abatement strategies have risks and uncertainties which could lead to repeating waves of infection. We show-as proof of concept grounded on rigorous mathematical evidence-that periodic, high-frequency alternation of into, and out-of, lockdown effectively mitigates second-wave effects, while allowing continued, albeit reduced, economic activity. Periodicity confers (i) predictability, which is essential for economic sustainability, and (ii) robustness, since lockdown periods are not activated by uncertain measurements over short time scales. In turn-while not eliminating the virus-this fast switching policy is sustainable over time, and it mitigates the infection until a vaccine or treatment becomes available, while alleviating the social costs associated with long lockdowns. Typically, the policy might be in the form of 1-day of work followed by 6-days of lockdown every week (or perhaps 2 days working, 5 days off) and it can be modified at a slow-rate based on measurements filtered over longer time scales. Our results highlight the potential efficacy of high frequency switching interventions in post lockdown mitigation. All code is available on Github at https://github.com/V4p1d/FPSP_Covid19. A software tool has also been developed so that interested parties can explore the proof-of-concept system.

Distributed ledgers have been proposed for a number of applications in the Internet-of-Things domain where it is essential to have an immutable and irreversible record of transactions. Directed acyclic graph (DAG)-based architectures, in particular, seem to provide a vast array of advantages over the more traditional Blockchain; however, it can be challenging to conduct a thorough analysis of DAG-based ledgers and derive reliable performance guarantees. In this article, we analyze one commonly discussed attack scenario known as the parasite chain attack, which aims at disrupting the immutability and irreversibility of the ledger, in the context of the IOTA Foundation's DAG-based system. Using a Markov chain model, we study the vulnerabilities of IOTA's core tip selection method against this attack and we present an extension of the algorithm to improve the resilience of the ledger in this scenario.

In the last two decades, thanks to the considerable technological development of solid-state sensors, digital holography (DH) has gained credits as the elective imaging technique for applications in various research fields, e.g., material science, biotechnology, as well as a diagnostic tool for applications at lab-on-a-chip scale. However, since its beginning, the intrinsic coherent nature of holography made 3-D imaging and display one of its preferred applications. Still today, several research groups around the world are working to develop novel numerical solutions in the framework of DH-based 3-D imaging and display technology. In this paper, we report an overview of the most important contributions given to this field over the last years.

In this paper we used clustering algorithms to compare the typical load profiles of different European countries in different day of the weeks. We find out that better results are obtained if the clustering is not performed directly on the data, but on some features extracted from the data. Clustering results can be exploited by energy providers to tailor more attractive time-varying tariffs for their customers. In particular, despite the relevant differences among the several compared countries, we obtained the interesting result of identifying a single feature that is able to distinguish weekdays from holidays and pre-holidays in all the examined countries.

Today, fast and accurate diagnosis through portable and cheap devices is in high demand for the general healthcare. Lab-on-chips (LoCs) have undergone a great growth in this direction, supported by optical imaging techniques more and more refined. Here we present recent progresses in developing imaging tools based on coherent imaging microscopy that can be very useful when applied into biomicrofluidics. In some cases, the optical tweezers (OT) technique is combined with digital holography (DH), thus offering the possibility to manipulate, analyze, and measure fundamental parameters of different kinds of cells. This approach can open the route for rapid and high-throughput analysis in label-free microfluidic devices and for prognostic based on cell examination, thus allowing advancements in biomedical science.