Skip to Content
Artificial intelligence

Software that swaps out words can now fool the AI behind Alexa and Siri

An image of words
An image of wordsJon Fife | Flickr

The news: Software called TextFooler can trick natural-language processing (NLP) systems into misunderstanding text just by replacing certain words in a sentence with synonyms. In tests, it was able to drop the accuracy of three state-of-the-art NLP systems dramatically. For example, Google’s powerful BERT neural net was worse by a factor of five to seven at identifying whether reviews on Yelp were positive or negative.

They tested the attack on NLP systems trained to do tasks such as identify news topics, detect fake news, and analyze sentiment. In all cases, the AI became significantly worse.

How it works: The software, developed by a team at MIT, looks for the words in a sentence that are most important to an NLP classifier and replaces them with a synonym that a human would find natural. For example, changing the sentence “The characters, cast in impossibly contrived situations, are totally estranged from reality” to “The characters, cast in impossibly engineered circumstances, are fully estranged from reality” makes no real difference to how we read it. But the tweaks made an AI interpret the sentences completely differently. 

Why it matters: We have seen many examples of such adversarial attacks, most often with image recognition systems, where tiny alterations to the input can flummox an AI and make it misclassify what it sees. TextFooler shows that this style of attack also breaks NLP, the AI behind virtual assistants—such as Siri, Alexa and Google Home—as well as other language classifiers like spam filters and hate-speech detectors. The researchers say that tools like TextFooler can help make NLP systems more robust, by revealing their weaknesses.

Deep Dive

Artificial intelligence

Why Meta’s latest large language model survived only three days online

Galactica was supposed to help scientists. Instead, it mindlessly spat out biased and incorrect nonsense.

DeepMind’s game-playing AI has beaten a 50-year-old record in computer science

The new version of AlphaZero discovered a faster way to do matrix multiplication, a core problem in computing that affects thousands of everyday computer tasks.

A bot that watched 70,000 hours of Minecraft could unlock AI’s next big thing

Online videos are a vast and untapped source of training data—and OpenAI says it has a new way to use it.

Stay connected

Illustration 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.