{"pk":28733,"title":"A Surprising Density of Illusionable Natural Speech","subtitle":null,"abstract":"Recent work on adversarial examples demonstrates a brittleness of many state-of-the-art machine learning systems. Weinvestigate one human analog, asking: What fraction of natural speech can be turned into illusions which alter humans per-ception or result in different people having significantly different perceptions? Using generated videos, we first empiricallyestimate that 17% of words occurring in natural speech have some susceptibility to the McGurk effect–the phenomenonby which adding a carefully chosen video clip to the audio channel affects the viewers perception of the message. We de-velop a bag-of-phonemes prediction model for word-level illusionability that we extend with natural language modeling tobuild a sentence-level framework. We train an instantiation using Amazon Mechanical Turk evaluations on sentence-levelillusions. Finally we generate several new instances of the Yanny/Laurel illusion, demonstrating that it is not an isolatedoccurrence. The surprising density of illusionable instances warrants further investigation from cognitive and securityperspectives.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Papers with Poster Presentations","is_remote":true,"remote_url":"https://escholarship.org/uc/item/1f32959f","frozenauthors":[{"first_name":"Melody","middle_name":"Y.","last_name":"Guan","name_suffix":"","institution":"Stanford University","department":""},{"first_name":"Gregory","middle_name":"","last_name":"Valiant","name_suffix":"","institution":"Stanford University","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2019-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/28733/galley/18604/download/"}]}