'Mind hackers' could get secrets from your brainwaves

'Mind hackers' could get secrets from your brainwaves

Summary: Security researchers have used cheap Emotiv headsets to capture people's subconscious responses to stimuli and use them to uncover data directly from their subjects' brains. It's a theoretical risk to privacy and security that could become significant with further advances in technology


Could hackers get access to your bank details and PIN codes by reading your mind? It wouldn't be easy, but computer scientists reckon its theoretically possible using wireless EEG headsets like Emotiv's Epoc, which costs only $299. These are not yet mass-market devices, but people who use headsets to play games and control devices such as wheelchairs could conceivably have their brains hacked if they download rogue applications.

Ivan Martinovic, from the University of Oxford, explored the idea in his talk at the Usenix Security Symposium held in Seattle earlier this month (video). The team behind the research -- which also included members from the University of California at Berkeley and the University of Geneva -- has published at paper: On the Feasibility of Side-Channel Attacks with Brain-Computer Interface (PDF).

Emotiv EPOC headset in use
Emotiv EPOC headset in use

One aim of the research was to explore whether or not EEG headsets represented a threat to privacy. While there are many such headsets available, they used the Emotiv device because of its low cost and because the company makes its API available to researchers, and it has a software development kit (SDK) for developers.

Outside of medicine, where researchers have been studying electro-encephalograms for decades, EEG headsets are most often used for games and for control applications or both. For example, someone can use their brainwaves to shoot virtual fireballs in the Arena game, or to control a real toy helicopter. Usually, the control process involves mastering one command at a time, and facial expressions can be used, such as winks and smiles.

Beyond that, the brain responds naturally to external stimuli. One of the most useful is the P300 recognition response that peaks about 300 milliseconds after the user recognises something relevant. The team developed a recognition model by, for example, showing test subjects photographs of people they didn't know, and then showing them a face they did know: Barack Obama.

After that, you can try to detect unknown data. For example, if you had test subjects and photographs of their homes, you could find out who lived where by showing them the pictures and looking for the recognition response. The team did find homes correctly about 60 percent of the time.

emotiv headset

By showing people images related to credit cards, PINs and so on, a hacker might also be able to discover private banking details. The researchers don't claim to have done this, but Martinovic told the symposium that "we could actually perform better than a pure random guess". They are now looking at "more sophisticated attacks".

The system could also be used for market research, or for interrogation purposes. For example, you could test a suspect with photographs of crime scenes, or rape victims.

Martinovic said: "we're interested in subconscious responses. Even if you try to lie, you will actually need more attention, and this will produce a better signal for us to detect."

Brainwaves are messy things to track, and a lot of pre-processing is required to extract a signal from the noise. Also, EEG headsets such as Emotiv's are not optimised to capture P300 signals. However, one day, brain hackers might be able to get useful signals without a subject's co-operation, perhaps by a combination of face- and brain-scanning. That really would be a threat to privacy.


Tan Le, Emotiv's co-founder, showed Epoc in a TED talk: A headset that reads your brainwaves 



Topics: Emerging Tech, Security

Jack Schofield

About Jack Schofield

Jack Schofield spent the 1970s editing photography magazines before becoming editor of an early UK computer magazine, Practical Computing. In 1983, he started writing a weekly computer column for the Guardian, and joined the staff to launch the newspaper's weekly computer supplement in 1985. This section launched the Guardian’s first website and, in 2001, its first real blog. When the printed section was dropped after 25 years and a couple of reincarnations, he felt it was a time for a change....

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.


Log in or register to join the discussion
  • so stupid people are gonna win in the end

    your thoughts cant be read if you dont have any
  • 'Mind hackers' could get secrets from your brainwaves

    at least we will something stupid, i guess...
  • Ivan Martinovic, from the University of Oxford should be fired today!

    This article sounds so ridicules that anyone with half a brain would call BS on it. I'm sure Ivan almost cummed himself when he came up with "Usenix Security Symposium", words that mean absolutely nothing. I personally just invented the "Coruscant Luminescent Accoutrement" or in other words a blinking flashlight.

    Here is the problem: at this point in time we can barely tell left from right using that device. As the test states, they figured out if the picture is relevant by the response time not any actual useful information. You can most likely get the same amount on relevant information from the facial expression, unless they have a really good porker face. =P

    I hate dumb assholes with their heads in the sky, thinking they're smart by slapping few big words together and vaguely claiming that they once predicted something that was latter actually proven scientifically.

    I claim that you can make Gold out of Lead. Once they figure out how to do this, with millions of man hours of research, I'll just claim I was the master mind behind this because I once claim this could have been possible.
  • Go Easy on Ivan

    As I read the article, it seems that he is projecting FUTURE developments, not simply analyzing the CURRENT state of the (experimental) art. You seem to have the attitude of the government bureaucrat who asked Michael Faraday what good his complicated, inefficient machine to turn magnetism+motion into electric current would be. He is rumored to have made one of two replies, both prescient: either "what good is a newborn babe?" or "some day you will tax it." Used any utility power or started your car today?

    Similarly, when Ampex patented its huge, rack-mounted video recorder requiring 2-inch wide tape on 2-foot reels, and only suitable for use within a TV studio, they sold for a pittance the rights to use it outside the studio, to a Japanese company called Sony. The movie watching history of the '80s and '90s tells you what they did with those rights.

    So, the author is speculating about what COULD happen as the technology is expanded further and becomes more reliable, not what is actually feasible NOW. I remember as an engineering student in the '60s that voice and visual pattern recognition algorithms were very primitive (I assisted in some very early pattern recognition projects), and now I have an Android phone that can take a picture of a strange chessboard-like square pattern and almost instantly go to a web site; I do not currently have an iPhone with Siri, or the Dragon software, but considering they would take hundreds of dollars of CPU time on a 60's mainframe to process ONE WORD, they have certainly advanced. And brain wave analysis is basically a pattern recognition problem. I am looking forward to "Dragon Naturally Thinking" coming on the market within ten years or so. But to protect my next novel (LOL), I will also want a great firewall to go with it!

    I'm an electronic and software engineer with a medical school education and a particular interest in neurology and neuro-electrophysiology. I've worked on quantum magnetoencephalography projects at the NIH. I have consumer brainwave sensors and have experimented with the APIs.

    I can tell you without a shadow of a doubt that this article is LAME, LAME, LAME. The notion is complete bullshit. They've gone from a failed laboratory experiment in recognizing houses using cooperative subjects submitting to the picture-exposure protocol and barely being correct more than 50% of the time, and then took a leap to hackers figuring out your bank account number through brainwaves, without your knowledge, while you're using some other application? I don't think so. Not by a long shot.

    These consumer products barely register anything at all. If reading anything from the mind is ever possible, it'll be done with 3-D dynamic field mapping, will be highly customized for the individual, and will NEVER work through surface EEG electrodes. Trying to read any thing from the mind with surface EEG electrodes is like trying to follow a movie from an adjacent theater when all you have is the rumblings from the surround-sound subwoofers. Sure, if you already know the movie you can tell when the big battle scene is on, but that's about all.

    Future developments? Sure, anything is possible. But not with these devices and today's technology. And this article was talking about NOW.

    So give me a break.
  • Don't "go easy on Ivan"

    Jallan32, he definitely WASN'T talking about future developments. In the first paragraph he says. " ... computer scientists reckon its theoretically possible using wireless EEG headsets like Emotiv's Epoc, which costs only $299."

    No. Not a chance. Sure, you can read into it anything you want, but that's your fantasy, it's not what was written. As it stands, this article is complete horeseshit. See my other post for supporting detail.