Cybersecurity: Autonomous Cars - Salem73616C656D/reading-notes GitHub Wiki

Key Takeaways

ANY COMPUTER IS SUSCEPTIBLE TO HACKING

Any computer scientist knows that it is very difficult to create software without any bugs—especially when the software is very complex. Bugs may sometimes be security vulnerabilities, and may be exploitable. Hence, very complex systems such as self-driving cars might contain vulnerabilities that may be potentially exploited by hackers, or may rely on sensors for making decisions that may be tricked by hackers. For example, a road sign that looks like a stop sign to a human might be constructed to look like a different sign to the car. In fact, more and more research papers have been appearing lately that are demonstrating such tricks against machine learning systems.

Exploits for automated cars have already been created, and in 2015 a researcher developed a way to activate a cars brakes while it was driving. Potentially in the future it will be more secure as researches figure out how to isolate a car from the outside world, but as it stands today it wouldn't be hard for an experienced hacker to break into your car and cause damage.

source