The rapid growth of electric vehicles on roads worldwide has driven the expansion of accessible and efficient charging infrastructure, but this expansion also introduces new cybersecurity risks that remain understudied and lack viable solutions. According to WIRED, researchers from the NICS lab at the University of Malaga in Spain have developed an innovative proposal to deploy AI agents to protect EV charging infrastructure from cyberattacks.
Cristina Alcaraz, an infrastructure-security researcher at the University of Malaga and lead author of the report, explained that the vulnerability of EV charging stations stems from their integration of multiple physical and digital components. This complex architecture, while keeping chargers efficient, also presents far-reaching security vulnerabilities. Attacks on chargers could compromise both EV adoption and the stability of electrical grids.
The AI Agent Solution
The researchers propose a system that uses multiple AI agents integrated into each charging station or relevant network component. These agents are capable of analyzing their environment, collecting information, and collaborating with other agents to build a comprehensive view of the infrastructure's present state. "Each agent assesses the status of chargers, communications, and connected devices to detect anomalies, operational failures, or potential security incidents," Alcaraz said. The agents are connected to a central monitoring system and compare locally obtained information with nearby stations, providing a more complete, accurate, and contextualized collaborative view.
Leveraging the Open Charge Point Protocol
The team's proposal ensures early and reliable detection of anomalies and attacks using the Open Charge Point Protocol (OCPP) , one of the most widely used standards for EV charger operation and management. OCPP allows a network of charging stations to communicate with a centralized system that manages user authentication, electrical load management, consumption monitoring, and technical diagnostics. However, current monitoring mechanisms based on OCPP typically focus only on network traffic or local events, offering a limited view. The researchers note this makes it difficult to identify where an anomaly is occurring, which components are compromised, and how an attack might spread.
Consensus Through Opinion Dynamics
One of the most novel features of the system is its use of a consensus mechanism based on a mathematical framework known as opinion dynamics. This approach mimics how humans exchange information within social networks to reach agreements. When applied to computer models, it allows AI agents to share observations and gradually adjust their assessments to build a collective understanding of the overall situation. The work was published in the International Journal of Critical Infrastructure Protection.
Threats Addressed
The AI agents are designed to prevent cyberattacks from different vectors, including:
- Fraud or energy theft by malicious actors using charging stations.
- Larger attacks that could damage critical energy networks.
The system aims to detect anomalies early, preventing both localized theft and broader grid disruptions.
Implications for Enterprise Technology Leaders
For CTOs and digital transformation leaders overseeing charging infrastructure or related IoT deployments, this research highlights a proactive approach to cybersecurity. Instead of passive monitoring, AI agents that collaborate and use consensus can provide a more resilient defense. The reliance on an open standard (OCPP) also suggests that such solutions could be integrated into existing systems without vendor lock-in. While the proposal is still research-stage, it points toward a future where distributed AI guards critical infrastructure against evolving threats.
Sources:
