Hackers can trick a Tesla into accelerating by 50 miles per hour - MIT Technology Review
▻https://www.technologyreview.com/s/615244/hackers-can-trick-a-tesla-into-accelerating-by-50-miles-per-hour
Hackers have manipulated multiple Tesla cars into speeding up by 50 miles per hour. The researchers fooled the car’s MobilEye EyeQ3 camera system by subtly altering a speed limit sign on the side of a road in a way that a person driving by would almost never notice.
This demonstration from the cybersecurity firm McAfee is the latest indication that adversarial machine learning can potentially wreck autonomous driving systems, presenting a security challenge to those hoping to commercialize the technology.
MobilEye EyeQ3 camera systems read speed limit signs and feed that information into autonomous driving features like Tesla’s automatic cruise control, said Steve Povolny and Shivangee Trivedi from McAfee’s Advanced Threat Research team.
The researchers stuck a tiny and nearly imperceptible sticker on a speed limit sign. The camera read the sign as 85 instead of 35 and, in testing, both the 2016 Tesla Model X and that year’s Model S sped up 50 miles per hour.
The modified speed limit sign reads as 85 on the Tesla’s heads-up display. A Mobileye spokesperson downplayed the research by suggesting this sign would fool a human into reading 85 as well.
MCAFEE
The Tesla, reading the modified 35 as 85, is tricked into accelerating.
MCAFEE
This is the latest in an increasing mountain of research showing how machine learning systems can be attacked and fooled in life-threatening situations.
“Why we’re studying this in advance is because you have intelligent systems that at some point in the future are going to be doing tasks that are now handled by humans,” Povolny said. “If we are not very prescient about what the attacks are and very careful about how the systems are designed, you then have a rolling fleet of interconnected computers which are one of the most impactful and enticing attack surfaces out there.”
As autonomous systems proliferate, the issue extends to machine learning algorithms far beyond vehicles: A March 2019 study showed medical machine-learning systems fooled into giving bad diagnoses.
A Mobileye spokesperson downplayed the research by suggesting the modified sign would even fool a human into reading 85 instead of 35. The company doesn’t consider tricking the camera to be an attack and, despite the role the camera plays in Tesla’s cruise control and the camera wasn’t designed for autonomous driving.
“Autonomous vehicle technology will not rely on sensing alone, but will also be supported by various other technologies and data, such as crowdsourced mapping, to ensure the reliability of the information received from the camera sensors and offer more robust redundancies and safety,” the Mobileye spokesperson said in a statement.
Comme je cherchais des mots clés, je me disais que « #cyberattaque » n’était pas le bon terme, car l’attaque n’est pas via le numérique, mais bien en accolant un stocker sur un panneau physique. Il ne s’agit pas non plus d’une attaque destructive, mais simplement de « rendre fou (footing) » le système de guidage, car celui-ci ne « comprend » pas une situation. La réponse de MobilEye est intéressante : un véhicule autonome ne peut pas se fier à sa seule « perception », mais recouper l’information avec d’autres sources.
#Machine_learning #Véhicules_autonomes #Tesla #Panneau_routiers #Intelligence_artificielle
