Skip to Content
Artificial intelligence

To protect artificial intelligence from attacks, show it fake data

Google Brain’s Ian Goodfellow explains how AI systems defend themselves, onstage at EmTech Digital
March 27, 2018

AI systems can sometimes be tricked into seeing something that’s not actually there, as when Google’s software “saw” a 3-D-printed turtle as a rifle. A way to stop these potential attacks is crucial before the technology can be widely deployed in safety-critical systems like the computer vision software behind self-driving cars.

At MIT Technology Review’s annual EmTech Digital conference in San Francisco this week, Google Brain researcher Ian Goodfellow explained how researchers can protect their systems.

Goodfellow is best known as the creator of generative adversarial networks (GANs), a type of artificial intelligence that makes use of two networks trained on the same data. One of the networks, called the generator, creates synthetic data, usually images, while the other network, called the discriminator, uses the same data set to determine whether the input is real. Goodfellow went through nearly a dozen examples of how different researchers have used GANs in their work, but he focused on his current main research interest, defending machine-learning systems from being fooled in the first place. He says for earlier technologies, like operating systems, defense of the technology was added afterwards, a mistake he doesn’t want made with machine learning.

“I want it to be as secure as possible before we rely on it too much,” he says.

GANs are very good at creating realistic adversarial examples, which end up being a very good way to train AI systems to develop a robust defense. If systems are trained on adversarial examples that they have to spot, they get better at recognizing adversarial attacks. The better those adversarial examples, the stronger the defense.

Goodfellow says these concerns are still theoretical and that he hasn’t heard of adversarial examples being used to attack computer vision systems, but bots or spammers are trying to use similar methods to look like more legitimate traffic and accomplish their goals.

Luckily, Goodfellow says, there is still time to prepare our systems to defend themselves from AI-enabled attacks.

“So far, machine learning isn’t good enough to be used in attacks," he says.

Deep Dive

Artificial intelligence

conceptual illustration showing various women's faces being scanned
conceptual illustration showing various women's faces being scanned

A horrifying new AI app swaps women into porn videos with a click

Deepfake researchers have long feared the day this would arrive.

storm front
storm front

DeepMind’s AI predicts almost exactly when and where it’s going to rain

The firm worked with UK weather forecasters to create a model that was better at making short term predictions than existing systems.

People are hiring out their faces to become deepfake-style marketing clones

AI-powered characters based on real people can star in thousands of videos and say anything, in any language.

computation concept
computation concept

How AI is reinventing what computers are

Three key ways artificial intelligence is changing what it means to compute.

Stay connected

Illustration by Rose WongIllustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.