Nov 9, 2018

Machine learning could protect AV systems from cyberattacks

Illustration: Sarah Grillo/Axios

With cars further evolving from “just” hardware into software platforms, the wide range of IT systems in an autonomous vehicle present many opportunities for cyberattacks. Artificial intelligence, especially machine learning technologies, can detect anomalous vehicle behavior or attempted code interference in real time.

Why it matters: Compromised code in the systems that control acceleration, braking, directional guidance and other crucial safety functions can jeopardize lives on the road.

Inside a hack:

  • After hackers breach an AV’s system, they can identify vulnerabilities, infect additional areas of the vehicle, and collect and extract data.
  • Their malicious goals could include anything from tracking the vehicle's movements (perhaps with an eye toward robbing passengers or burglarizing their homes when they are far enough away) to disabling its brakes, putting people both inside and around the vehicle in danger.
  • Embedded, stealth malware in the vehicle's network and in the units that control its IT and electronic subsystems could generate atypical activity, such as fluctuations in the number of bytes sent or the amount of memory being used.
  • Example: Hackers could install malware in a truck that activates when it determines — via the vehicle's cameras and sensors — the truck is in an isolated section of highway. The truck could be forced to stop, allowing criminals in another vehicle to corner it and abscond with the loot. 

How AI detection might help:

  • AI uses data from the vehicle's network and central computers to learn its normal behavior, typically before the vehicle is mass-produced. Algorithms can then process operating data to identify and flag any abnormal behavior as a potential cyberattack, triggering safety systems that can intervene.
  • These algorithms need to distinguish between real attacks and false positives, such as when a vehicle owner has modified the software for speed or other safety precautions.

What to watch: Attacks on AVs could spur a “horse race” between developers trying to continually improve traditional security measures and hackers developing more sophisticated attacks to upend these security systems.

Yossi Vardi is the CEO of SafeRide Technologies, an automotive cybersecurity startup.

Go deeper

The cost of going after Bloomberg

Illustration: Eniola Odetunde/Axios

Here's the growing dilemma for 2020 Democrats vying for a one-on-one showdown with frontrunner Bernie Sanders: Do they have the guts — and the money — to first stop Mike Bloomberg?

Why it matters: Joe Biden, Pete Buttigieg, Amy Klobuchar and Elizabeth Warren all must weigh the costs of punching Bloomberg where he looks most vulnerable: stop-and-frisk, charges of sexism, billionaire entitlement. The more zealous the attacks, the greater the risk he turns his campaign ATM against them.

How Trump’s economy stacks up

Source: "Presidents and US Economy", Trump figures through 2019 courtesy of Alan Blinder; Note: Data shows real GDP and Q1 growth in each term is attributed to the previous president; Chart: Axios Visuals

Average economic growth under President Trump has outpaced the growth under Barack Obama, but not all of his recent predecessors.

Why it matters: GDP is the most comprehensive economic scorecard — and something presidents, especially Trump, use as an example of success. And it's especially relevant since Trump is running for re-election on his economic record.

Coronavirus cases rise as 14 American evacuees infected

Data: The Center for Systems Science and Engineering at Johns Hopkins, the CDC, and China's NHC; Note: China refers to mainland China and the Diamond Princess is the cruise ship offshore Yokohama, Japan. Map: Danielle Alberti/Axios

14 Americans evacuated from the Diamond Princess cruise ship tested positive for the novel coronavirus before being flown in a "specialist containment" on a plane repatriating U.S. citizens back home, the U.S. government said early Monday.

The big picture: COVID-19 has now killed at least 1,770 people and infected almost 70,000 others. Most cases and all but five of the deaths have occurred in mainland China. Taiwan confirmed its first death on Sunday, per multiple reports, in a 61-year-old man with underlying health conditions. Health officials were investigating how he became ill.

Go deeperArrowUpdated 2 hours ago - Health