Fooling NLP Systems Through Word Swapping
Schneier on Security 2020-04-28
Summary:
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...
Link:
https://www.schneier.com/blog/archives/2020/04/fooling_nlp_sys.htmlFrom feeds:
Berkman Center Community - Test » Schneier on SecurityGudgeon and gist » Schneier on Security