Researchers can now send secret audio instructions undetectable to the human ear.
Technology News : Many people have grown accustomed to talking to their smart devices, asking them to read a text, play a song or set an alarm. But someone else might be secretly talking to them, too.
Over the past two years, researchers in China and the United States have begun demonstrating that they can send hidden commands that are undetectable to the human ear to Apple’s Siri, Amazon’s Alexa and Google’s Assistant. Inside university labs, the researchers have been able to secretly activate the artificial intelligence systems on smartphones and smart speakers, making them dial phone numbers or open websites. In the wrong hands, the technology could be used to unlock doors, wire money or buy stuff online — simply with music playing over the radio.
A group of students from University of California, Berkeley and Georgetown University showed in 2016 that they could hide commands in white noise played over loudspeakers and through YouTube videos to get smart devices to turn on airplane mode or open a website.
This month, some of those Berkeley researchers published a research paper that went further, saying they could embed commands directly into recordings of music or spoken text. So while a human listener hears someone talking or an orchestra playing, Amazon’s Echo speaker might hear an instruction to add something to your shopping list.
“We wanted to see if we could make it even more stealthy,” said Nicholas Carlini, a fifth-year PhD student in computer security at U C Berkeley and one of the paper’s authors.
Carlini added that while there was no evidence that these techniques have left the lab, it may only be a matter of time before someone starts exploiting them.
These deceptions illustrate how artificial intelligence — even as it is making great strides — can still be tricked and manipulated. Computers can be fooled into identifying an airplane as a cat just by changing a few pixels of a digital image, while researchers can make a self-driving car swerve or speed up simply by pasting small stickers on road signs and confusing the vehicle’s computer vision system.
With audio attacks, the researchers are exploiting the gap between human and machine speech recognition. Speech recognition systems typically translate each sound to a letter, eventually compiling those into words and phrases. By making slight changes to audio files, researchers were able to cancel out the sound that the speech recognition system was supposed to hear and replace it with a sound that would be transcribed differently by machines while being nearly undetectable to the human ear.
The proliferation of voice-activated gadgets amplifies the implications of such tricks. Smartphones and smart speakers that use digital assistants such as Amazon’s Alexa or Apple’s Siri are set to outnumber people by 2021, according to the research firm Ovum. And more than half of all American households will have at least one smart speaker by then, according to Juniper Research.
