Read the original article: Fooling NLP Systems Through Word Swapping
MIT researchers have built a system that fools natural-language processing systems by swapping words with synonyms: 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…
Read the original article: Fooling NLP Systems Through Word Swapping