Dark Reading is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Attacks/Breaches

2/19/2020
06:30 PM
Connect Directly
Twitter
LinkedIn
RSS
E-Mail
100%
0%

Researchers Fool Smart Car Camera with a 2-Inch Piece of Electrical Tape

McAfee researchers say they were able to get a Tesla to autonomously accelerate by tricking its camera platform into misreading a speed-limit sign.

Operators of some older Tesla vehicles might be surprised to learn that a single piece of two-inch black electrical tape is all it takes to trick the camera sensor in their cars into misinterpreting a 35-mph speed sign as an 85-mph sign.

Researchers at McAfee who discovered the issue said they were able to get a Tesla, equipped with version EyeQ3 of the Mobileye camera platform, to autonomously accelerate 50 miles above the speed limit.

The hack — which involved extending the middle of the "3" on the traffic sign with black tape — appears to only work on Teslas equipped with Mobileye version EyeQ3 (Tesla hardware Pack 1), according to McAfee. Attempts by the researchers to re-create the attack on Tesla models with the latest version of the Mobileye camera did not work. The newest Teslas no longer implement Mobileye technology, and they don't appear to support traffic sign recognition, McAfee said.

"We are not trying to spread fear here and saying that attackers are likely going to be driving cars off the road," says Steve Povolny, head of McAfee Advanced Threat Research. A Tesla model with the particular Mobileye version will reliably misinterpret the speed limit sign and attempt to accelerate to the misclassified speed limit if the driver has engaged traffic-aware cruise control, Povolny says. But the likelihood of that happening in a real-life situation without the driver becoming aware of the issue and taking control of the vehicle is remote, he says.

The real goal of the research is to raise awareness of some of the nontraditional threat vectors that are emerging with the growing integration of artificial intelligence (AI) and machine-learning (ML) capabilities in modern technologies. At the moment, hacks like these are still in the academic realm.

"If we project 10 to 20 years into the future, at some point these issues are going to be become very real," Povolny says. "If we have completely autonomous vehicles and computing systems that are making medical diagnosis without human oversight, we have a real problem space that is coming up."

Broader Research
McAfee's research involving Mobileye is part of a broader study the company is conducting into so-called "model hacking," or adversarial machine learning. The goal is to see whether weaknesses that are present in current-generation ML algorithms can be exploited to trigger adverse results. The Berryville Institute of Machine Learning (BIML) has classified adversarial attacks as one of the biggest risks to ML systems. In a recent paper, the think tank described adversarial attacks as being designed to fool a ML system by providing it with malicious input involving very small changes to the original data.

In the past, researchers have shown how an AI-powered image classification system can be tricked into misinterpreting a stop sign as a traffic speed limit sign using a few pieces of strategically placed tape on the sign. Before the hack involving Mobileye cameras, McAfee researchers found they could use a few pieces of tape to get an in-house image classifying system to misinterpret a stop sign as an added lane sign. They also discovered they could trick the image classifier into misinterpreting speed limit signs.

The researchers wanted to find out whether they could use the same techniques to trick a proprietary system. They focused on Mobileye because the company's cameras are currently deployed in some 40 million vehicles. In some vehicles the cameras are used to determine the speed limit and to feed that data into their autonomous driving or driver-assist systems.

Initially the researchers used four stickers on the speed limit sign to confuse the camera and found they could consistently fool the system into thinking it was a different speed limit than what it really was. They kept reducing the number of stickers on the sign until they discovered all they really needed was one piece of tape.

"What we have done is trigger some weaknesses that are often inherent in all types of machine-learning systems and the underlying algorithms," Povolny says.

The algorithms used by the Mobileye cameras, for instance, are very specifically trained off a set of data they expect to see, he says – for example, things like known traffic signs or objects in the environment. But that training can often leave gaps in the ability of the system to identify unknown or even slightly nonstandard input. "We basically leverage those gaps or blindspots in the algorithms themselves to cause them to misclassify," Povolny says.

According to McAfee, it informed Tesla and Mobileye of its research in September and October 2019, respectively. "Both vendors indicated interest and were grateful for the research but have not expressed any current plans to address the issue on the existing platform," McAfee said. "Mobileye did indicate that the more recent versions of the camera system address these use cases."

Related Content:

Check out The Edge, Dark Reading's new section for features, threat data, and in-depth perspectives. Today's featured story: "8 Things Users Do That Make Security Pros Miserable."

Jai Vijayan is a seasoned technology reporter with over 20 years of experience in IT trade journalism. He was most recently a Senior Editor at Computerworld, where he covered information security and data privacy issues for the publication. Over the course of his 20-year ... View Full Bio
 

Recommended Reading:

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
COVID-19: Latest Security News & Commentary
Dark Reading Staff 7/2/2020
Ripple20 Threatens Increasingly Connected Medical Devices
Kelly Sheridan, Staff Editor, Dark Reading,  6/30/2020
DDoS Attacks Jump 542% from Q4 2019 to Q1 2020
Dark Reading Staff 6/30/2020
Register for Dark Reading Newsletters
White Papers
Video
Cartoon
Current Issue
How Cybersecurity Incident Response Programs Work (and Why Some Don't)
This Tech Digest takes a look at the vital role cybersecurity incident response (IR) plays in managing cyber-risk within organizations. Download the Tech Digest today to find out how well-planned IR programs can detect intrusions, contain breaches, and help an organization restore normal operations.
Flash Poll
The Threat from the Internetand What Your Organization Can Do About It
The Threat from the Internetand What Your Organization Can Do About It
This report describes some of the latest attacks and threats emanating from the Internet, as well as advice and tips on how your organization can mitigate those threats before they affect your business. Download it today!
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2020-9498
PUBLISHED: 2020-07-02
Apache Guacamole 1.1.0 and older may mishandle pointers involved inprocessing data received via RDP static virtual channels. If a userconnects to a malicious or compromised RDP server, a series ofspecially-crafted PDUs could result in memory corruption, possiblyallowing arbitrary code to be executed...
CVE-2020-3282
PUBLISHED: 2020-07-02
A vulnerability in the web-based management interface of Cisco Unified Communications Manager, Cisco Unified Communications Manager Session Management Edition, Cisco Unified Communications Manager IM & Presence Service, and Cisco Unity Connection could allow an unauthenticated, remote attack...
CVE-2020-5909
PUBLISHED: 2020-07-02
In versions 3.0.0-3.5.0, 2.0.0-2.9.0, and 1.0.1, when users run the command displayed in NGINX Controller user interface (UI) to fetch the agent installer, the server TLS certificate is not verified.
CVE-2020-5910
PUBLISHED: 2020-07-02
In versions 3.0.0-3.5.0, 2.0.0-2.9.0, and 1.0.1, the Neural Autonomic Transport System (NATS) messaging services in use by the NGINX Controller do not require any form of authentication, so any successful connection would be authorized.
CVE-2020-5911
PUBLISHED: 2020-07-02
In versions 3.0.0-3.5.0, 2.0.0-2.9.0, and 1.0.1, the NGINX Controller installer starts the download of Kubernetes packages from an HTTP URL On Debian/Ubuntu system.