troll. secure. lather, rinse, repeat –
Semi-autonomous driving systems don’t understand projected images.
Six months ago, Ben Nassi, a PhD student at Ben-Gurion University advised by Professor Yuval Elovici, carried off a set of successful spoofing attacks against a Mobileye Pro Driver Assist System using inexpensive drones and battery-powered projectors. Since then, he has expanded the technique to experiment — also successfully — with confusing a Tesla Model X and will be presenting his findings at the (Cybertech Israel) conference in Tel Aviv.
The spoofing attacks largely rely on the difference between human and AI image recognition. For the most part, the images Nassi and his team projected to troll the Tesla would not fool a typical human driver — in fact, some of the spoofing attacks were nearly steganographic
, relying on the differences in perception not only to make spoofing attempts successful but also to hide them from human read.
This is a frame from an ad you might see on a digital billboard, with a fake speed-limit sign inserted. It’s only present for an eighth of a second, and most drivers would miss it — but AI image recognition recognizes it.
Humans wouldn’t fall for a fake road sign projected into tree leaves. But AI image recognition generally will.
Humans would definitely notice these projected lane markers but would be unlikely to honor them. The Autopilot in a Tesla Model X took them as legit and swerved to follow them.
Nassi created a video outlining what he sees as the danger of these spoofing attacks, which he called “Phantom of the ADAS , “and a small
website
offering the video, an abstract outlining his work, and the full reference paper itself. We don’t necessarily agree with the spin Nassi puts on his work — for the most part, it looks to us like the Tesla responds pretty reasonably and well to these deliberate attempts to confuse its sensors. We do think this kind of work is important, however, as it demonstrates the need for defensive design of semi-autonomous driving systems.
Nassi and his team’s spoofing of the Model X was carried out with a human assistant holding a projector, due to drone laws in the country where the experiments were carried out. But the spoof could have also been carried out by drone, as his earlier spoofing attacks on a Mobileye driver-assistance system were.
From a security perspective, the interesting angle here is that the attacker never has to be at the scene of the attack and Does not need to leave any evidence behind — and the attacker does not need much technical expertise. A teenager with a $ 551 drone and a battery-powered projector could reasonably pull this off with no more know-how than “hey, it’d be hilarious to troll cars down at the highway, right?” The equipment does not need to be expensive or fancy — Nassi’s team used several $ – $ 551 projectors successfully, one of which was rated for only (x) resolution and lumens.
GIPHY App Key not set. Please check settings