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.html

From feeds:

Berkman Center Community - Test » Schneier on Security
Gudgeon and gist » Schneier on Security

Tags:

Authors:

Bruce Schneier

Date tagged:

04/28/2020, 11:49

Date published:

04/28/2020, 11:38