The security of connected vehicles plays a pivotal role as they can be used to prevent life-threatening situations. A new system called VANET has been developed to prevent confusion of signals in connected autonomous vehicles.
A new system can protect autonomous vehicles from hackers by using artificial intelligence to secure wireless communications. We must secure self-driving vehicles, as autonomous vehicles work with countless data messages coming from each vehicle sensor per second. Another reason why safety of the autonomous vehicles is crucial is that the receiving signal should be legitimate. Without such safety, we can put human lives and connected autonomous vehicle systems at risk.
An Autonomous vehicle communicates with a complex network of sensors. When on road the self-driving vehicle must pass hundreds of connected autonomous vehicles, in such cases it must go sift through thousands of data messages from its sensors and by other connected autonomous vehicles on road. This can create confusion and this may lead to cars taking wrong turns or in the worst-case scenario it might cause multiple piles up of cars on roads. Also, hackers can use dummy transmitters to create false roadblocks.
To prevent such issues researchers at the University of Massachusetts proposed a method employing weighted sensor readings along with artificial intelligence to protect passengers in self-driving vehicles from erroneous or even malicious messages. This system is cheaper and requires less computation than other message verification systems.
The new system is called VANET. VANET is a wireless communication system. This system uses mobile cars as communication nodes to determine positioning and movement for connected vehicles.
By using systems like VANET, connected vehicles can validate every message that is being circulated in their network. To make sure that the messages being received are valid, the researchers created a system that augments message authentication with artificial intelligence. Here the AI analyses the data being provided by sensors. The AI will also identify the irregularities within the data.
However, the proposed system is not ready for deployment in connected autonomous vehicles because of a large amount of data transmission. The researchers believe that they can lower the number of missed messages which was 11%, by performing training using deep technique languages. The researchers are hoping to enhance the decision-making capability of the system.
So, more testing and research is required, but the autonomous driving future seems closer.
-by Jasmeen Gill
ICAV Cluster is Smart City and CAV news aggregator. To add your Smart City or CAV related news, please email our editorial team on firstname.lastname@example.org