Computer scientists have devised a way of making computer speech recognition safer from malicious attacks – messages that sound benign to human ears but hide commands that can hijack a device. Bo Li, a professor of computer science at Illinois, and her co-authors wrote an algorithm that transcribes a full audio clip and, separately, just one portion of it. If the transcription of that single piece doesn’t closely match the corresponding part of the full transcription, the program throws a red flag.
