A team of researchers at the MIT Computer Science & Artificial Intelligence Lab (CSAIL) recently released a framework called TextFooler which successfully tricked state-of-the-art NLP models (such as ...

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More AI and machine learning algorithms are vulnerable to adversarial samples ...

Researchers at MIT have created a framework—TextFooler—that brought down the prediction accuracy of certain NLP models from 90% down to under 20% by simply using synonyms in place of certain words.

There are plenty of examples of AI models being fooled out there. From Google’s AI to detect images mistaking a turtle for a gun to Jigsaw’s AI to score toxic comments tricked to think a sentence is ...