Here’s how AI agents can protect electric car chargers

number Electric vehicles On roads around the world it continues to grow. The boom in electric vehicle adoption has led to the development of accessible, fast and efficient charging infrastructure.

However, this expansion also brings with it new cybersecurity risks that have not been extensively studied, and for which there are still few viable solutions.

It’s a responsibility, explains Cristina Alcaraz, an infrastructure security researcher at the University of Malaga in Spain Electric car charging The terminals are due to the fact that they integrate multiple physical and digital components. She says this complex architecture not only keeps chargers running efficiently, but also introduces a host of new and far-reaching vulnerabilities. The vulnerability of chargers to attacks harms the continued adoption of electric vehicles as well as the stability of electrical grids in the countries where the chargers operate.

With the aim of addressing this threat, researchers from the NICS Laboratory at the University of Malaga have developed an innovative proposal for a deployment Artificial intelligence agents To protect infrastructure. These factors are designed to prevent cyberattacks from various vectors, ranging from fraud or power theft by malicious actors using charging stations to larger attacks that can damage critical power grids.

The team’s proposal aims to ensure early and reliable detection of anomalies and attacks on charging networks using Open the charging point protocol. The OCCP standard is one of the most widely used standards for the operation and management of electric vehicle chargers. The protocol allows a network of charging stations to communicate with a central system that can manage, monitor and coordinate all energy transactions made by end users.

The central system handles a range of things remotely, including user authentication, managing the electrical load at each station, monitoring overall electricity consumption, and technical diagnostics. These capabilities allow real-time control of infrastructure and enable operators to quickly detect and respond to any abnormal behavior.

However, the authors of the new study point out that current monitoring mechanisms based on this protocol typically focus only on network traffic or local events, so they can only provide a limited view of what is happening across an entire area of ​​infrastructure. This limitation makes it difficult to determine where anomalies occurred in a system, which network components have been compromised, the extent of any vulnerabilities, and the ways in which a potential attack might spread, researchers say.

Contact artificial intelligence

The researchers propose a system that uses multiple artificial intelligence agents. Each station or relevant component of the charging network includes artificial intelligence agents capable of analyzing its environment, gathering information, and collaborating with other agents in order to build a comprehensive view of the current state of the infrastructure.

“Each agent evaluates the health of chargers, communications, and connected devices to detect anomalies, operational failures, or potential security incidents,” says Alcaraz. “These agents, linked to a central monitoring system, compare information obtained locally with that at nearby stations, providing a more complete, accurate and context-sensitive collaborative view of the situation,” she says. Alcaraz is too Lead author of the report.

the job, published in International Journal of Critical Infrastructure ProtectionHe explains that one of the most modern features of the system is its use of a consensus mechanism based on a mathematical framework known as Opinion dynamics.

This approach mimics the processes by which humans exchange information within their social networks to reach agreements. When applied to computer models, it allows AI agents to share feedback with each other and gradually adjust their assessments to build a collective understanding of the overall situation.