Micropayments, involving low-value transactions (e.g., fractions of a euro/dollar), are critical for unlocking granular digital services. In this paper we present a novel highlevel architecture integrating artificial intelligence (AI) agents with the Bitcoin Lightning Network (LN) to enable efficient micropayments for electric vehicle (EV) charging and peer-to-peer energy trading. The proposed architecture leverages the ultra fast and low-cost nature of the LN to enforce trustless payments upon verified energy delivery. AI agents embedded in EVs and charging stations autonomously negotiate dynamic pricing and energy allocation using reinforcement learning (RL) approaches, optimizing grid load balancing and enhancing profitability compared to on-chain methods. Based on a comprehensive use case involving EV owners, operators and energy providers, we demonstrate the system’s viability, supported by a prototype implementation on the LN Testnet. Results show a $\mathbf{9 8. 2 \%}$ success rate for micropayments during simulated charging sessions, with AI agents reducing latency by prioritizing high-liquidity payment channels.

Pricing decisions in Supply Chain (SC) management play a crucial role in profit maximization. However, SC dynamics are increasingly complex and optimizing pricing-related decisions remains challenging due to centralized models that cause inefficiencies and slow adaptation. Trust issues between manufacturers and retailers, often driven by information asymmetry and data manipulation risks, also hinder proper SC coordination. In this paper we present a novel decentralized framework for dynamic pricing in SCs by integrating multi-agent reinforcement learning (MARL) with blockchain technology. We model the SC as a Stackelberg game where multiple manufacturers, acting as leaders, independently set wholesale prices and a single retailer, as the follower, adjusts retail prices to maximize profit. Each agent employs RL algorithms to iteratively learn optimal pricing strategies in response to evolving market conditions and competitor actions. The integration of a permissioned blockchain ensures that all pricing decisions, transactions and smart contract executions are immutably recorded, thus enhancing data integrity, security and transparency. Experimental evaluations under diverse market scenarios demonstrate that the proposed framework improves convergence rates, profit margins and system robustness. Our results highlight the potential of combining decentralized decision-making with tamper-proof ledger technology to foster trust and efficiency in complex SC ecosystems.

The emergence of Industry 4.0 technologies has significantly transformed supply chain operations, particularly through the deployment of Autonomous Guided Vehicles (AGVs) in logistics and manufacturing settings. Integrating Industrial Internet of Things (IIoT) devices with Artificial Intelligence (AI) has enhanced AGV autonomy by enabling real-time data-driven decision-making. However, challenges related to cybersecurity, data synchronization, and scalability, still persist in cyber-physical (CPS) manufacturing systems. Blockchain technology offers a prominent pathway towards ensuring data integrity, decentralization, and security, but its adoption in AGV applications remains limited due to scalability, latency, and computational constraints. To address this gap, this paper proposes a hybrid, blockchain-centric architecture that leverages the synergistic potential of Reinforcement Learning (RL) methods in multi-agent, collaborative AGVs. The architecture is designed to be scalable, interoperable, and resilient to cyber threats, making it suitable for a wide range of industrial applications.

The rise in cyber threats necessitates automated detection systems that can effectively identify and respond to hostile techniques. This paper presents a feasibility assessment of adopting Large Language Models (LLMs) to enhance cyber-security operations within the MITRE ATT&CK framework. We research how AI can automate Kusto Query Language (KQL) development to better cyber threat detection in Microsoft Sentinel. We start with prompt engineering to improve AI-generated queries, then compare LLMs to determine the top models. Through successive breakthroughs, we progressed from a naïve prompting method to an advanced Chain of Thought (CoT) prompting technique, enabling AI models to give more contextually accurate and structured KQL queries. We extensively tested both open-source and closed-source models, evaluating their performance using two separate accuracy scoring formulae. Our results demonstrate that CoT significantly enhances the precision of AI-generated queries, while ChatGPT-4o-mini surpasses other models in generating structured KQL queries. Our technology leverages real-time MITRE ATT&CK Intelligence and Microsoft Sentinel log analysis for automated threat identification and response in order to minimize human effort and enhance productivity. Our approach applies AI to automate cybersecurity tasks, whereas most other research on LLM-assisted security analytics remains theoretical and thus fills an important gap between theory and practice.

The increasing integration of Internet of Things (IoT) devices in various sectors has created complex and dynamically changing interconnected systems. In several multiauthority and multidomain applications, IoT devices may continuously change their connectivity status, leading to dynamic topologies; an IoT device may be connected to different gateways at different times, to support the provisioning of a distributed service. However, these complex environments increase exposure to security threats, such as device spoofing or cloning attacks. Even worse, without continuous device inventorying, an adversary may easily duplicate a cloned device and concurrently connect compromised Sybil nodes at different gateways, without getting noticed. This article proposes Hardware-assisted, continuous authentication and attestation protocol (HA-CAAP), a hardware-assisted continuous authentication and attestation protocol for IoT devices. By using a physically unclonable function-based periodic authentication mechanism, gateways can continuously authenticate their connected devices and detect modifications in their connectivity status, in nearly real-time. Through a private blockchain, gateways are able to continuously exchange information about their connectivity state and securely share a dynamic device inventory, to detect possible Sybil attacks. In addition, by integrating a continuous gateway attestation mechanism in the blockchain, the protocol prevents nontrusted gateways from joining in and assures their integrity. To evaluate HA-CAAP, security is formally analyzed, while a proof-of-concept implementation is used to analyze the protocol’s performance, for realistic application scenarios.

Companies in the supply chain recognize Enterprise Resource Planning (ERP) software as an indispensable component of their businesses that significantly helps with planning, decision-making, and cost reductions. However, despite the benefits of ERP, the interaction between supply chain stakeholders with varying and even contradictory security and privacy requirements could be challenging. In addition, incorporating a cross-domain access control might be hard because parties may require different access levels for information maintained outside their own ERP. In this work, we propose a blockchain architecture that acts as a service layer on top of existing ERP systems to achieve fine-grained intra- and cross-domain access control. A private blockchain is combined with four fully functional Smart Contracts to enable access control and trust management services, a data handler service, ensuring data integrity for both insiders and outsiders, and an audit mechanism.

The Internet of Medical Things (IoMT) provides ubiquitous healthcare services for patient monitoring and treatment. However, the interaction between doctors, patients, healthcare personnel and device manufacturers, with different and often conflicting security and privacy objectives, make such services vulnerable and subject to exploitation. In addition, since parties may require different access levels and the IoMT devices involve different functionalities, access control can be challenging. In this paper, we propose a blockchain-enabled authorization framework for managing both IoMT devices and medical files by creating a distributed chain of custody and health data privacy scheme. The core idea is to build trust domains for the various stakeholders and IoMT devices, in such a way that fine-grain access is enabled by taking into account critical attributes of the IoMT ecosystem such as a) the different roles and capabilities of the IoMT devices and b) their interaction with the users/stakeholders. A private blockchain is used in combination with on-chain smart contracts to allow for a forensics-by-design management architecture with audit trails for integrity and provenance guarantees as well as health data privacy. The private blockchain ecosystem is authenticated by a proof-of-medical-stake consensus mechanism that is tailored for medical applications.