Smart vehicles just got a new layer of protection: an AI system that can block nearly all cyber-attacks on connected transport networks.
Known as LFT-IDS (Label Flipping against Deep Learning Intrusion Detection System), the tool uses artificial intelligence to spot and block malicious data before it can disrupt vehicle operations.
This is especially useful for autonomous or networked combat vehicles, where any disruption could compromise the mission.
The system works by monitoring streams of sensor data, including temperature, tire pressure, and location, learning how sensors behave under normal conditions.
When hackers try to inject false or manipulated information, it automatically detects the anomaly and cuts it off, preventing unsafe actions or network disruptions.
Designed for cloud-connected environments, LFD-IDS acts as a filter at the network level, stopping malicious signals from reaching deeper into vehicle systems.
“Traditional intrusion detection methods face significant challenges in identifying new and previously unseen attacks,” said Dr. Rahim Taheri, senior lecturer at the University of Portsmouth’s School of Computing.
“However, by integrating machine learning capabilities in intrusion detection systems, we have shown that it is possible to substantially improve the accuracy in detecting threats.”
When Connectivity Becomes a Risk
Modern vehicles rely on dense networks of sensors feeding data to onboard computers and external traffic management tools.
While this connectivity improves safety and traffic flow, it also expands the attack surface.
With more data now moving through 4G and 5G networks, malicious interference becomes an increasing concern.
Researchers warn that falsified data could cause a vehicle to misinterpret its surroundings or behave unpredictably, putting critical operators and personnel at risk.
LFD-IDS was developed by researchers from the University of Portsmouth, the University of Reading, and Italy’s Consiglio Nazionale delle Ricerche.
