MIT Shows How Image Recognition AI Can Be Easily Fooled By Just Changing A Few Pixels

M

With artificial intelligence being such a huge revenue potential these days, technology companies are quick to point out how well their own particular versions function, whether that’s in computer vision, facial recognition, or otherwise.

However, they all currently possess one major flaw that can be exploited.

Unlike human observers, computer vision algorithms can be thrown off the mark by something called “adversarial example”. These are optical illusions specifically designed to fool computers into thinking a photo of one thing is actually something else.

So what if a computer can be fooled into thinking a frog is a cat right? How much harm can that do? Well the same method can also mess with a self-driving car’s AI for instance, making it mistake a stop sign for a speed limit indicator

According to new research by MIT’s Computer Science and Artificial Intelligence Laboratory, these adversarial examples are actually much easier to create than previously thought. Last week, the team managed to reliably fool Google’s Cloud Vision API, a commonly used algorithm today even under “black box conditions. Basically, that means they fooled the AI without the benefit of insight into how it functions and processes data.

Why an error-free vision processing AI is critical

In this particular case, they targeted the part of the AI that puts identifier labels to objects in a photo, like labelling a picture with a kitten in it as “cat”. After a trial and error process, they were able to manipulate Google’s computer vision system into thinking a row of machine guns was a helicopter. And they say the label they choose isn’t really important, they can reliably make an AI think an object is something totally different, just by tweaking pixels in the photo. The final image looks exactly the same to the naked eye, but it still confuses a machine learning algorithm.

In this way, the experiment demonstrates that attackers can fairly easily create these kinds of adversarial examples to confuse image recognition AI. For instance, an automated baggage scanner can be fooled into thinking a bomb in a suitcase is actually a teddy bear, or facial recognition at the gates can let someone else through on your ticket.

Thankfully, Google is already aware of and working on trying to fix this issue. Indeed, input from MIT’s research help puts that work a step closer to its final goal. However, it might be a few years before we see some significant breakthrough. Until then, don’t expect AI to play too large a part in automated functions.

Source link

37 comments

  • Magnificent beat ! I would like to apprentice while you amend your site, how can i subscribe for a blog website?
    The account aided me a acceptable deal. I had been tiny bit acquainted of this your broadcast provided bright clear concept

  • Hello my friend! I wish to say that this post is awesome, nice written and come with
    approximately all significant infos. I’d like to peer extra posts like this .

  • It’s going to be finish of mine day, except before finish I am reading this
    wonderful piece of writing to increase my experience.

  • Hey are using WordPress for your site platform? I’m new
    to the blog world but I’m trying to get started and set
    up my own. Do you need any coding knowledge to make your
    own blog? Any help would be greatly appreciated!

  • Wonderful work! This is the kind of information that are
    meant to be shared around the web. Shame on the seek
    engines for no longer positioning this post upper! Come on over and visit
    my site . Thanks =)

  • You can definitely see your expertise within the article you write.

    The world hopes for more passionate writers like you who are not afraid to mention how they believe.

    Always go after your heart.

  • Hmm it seems like your blog ate my first comment (it was extremely long) so I guess I’ll just sum it up what I had written and say, I’m thoroughly enjoying your blog.
    I too am an aspiring blog blogger but I’m still new to everything.
    Do you have any helpful hints for first-time blog
    writers? I’d definitely appreciate it.

  • Howdy! This article could not be written much better!
    Reading through this article reminds me of my previous roommate!
    He constantly kept talking about this. I’ll
    send this article to him. Fairly certain he’s going to have a great read.
    Thank you for sharing!

  • Wow, superb blog format! How lengthy have you been running a blog for?
    you made blogging glance easy. The whole glance of your web site is fantastic, let alone the content!

  • When I initially commented I clicked the “Notify me when new comments are added”
    checkbox and now each time a comment is added I
    get several emails with the same comment. Is there any way
    you can remove me from that service? Thank you!

  • Thank you a bunch for sharing this with all of us you actually realize what you are speaking about!
    Bookmarked. Kindly also visit my web site =). We may have a hyperlink trade agreement among us

  • Hmm is anyone else having problems with the pictures on this
    blog loading? I’m trying to figure out if its a problem
    on my end or if it’s the blog. Any responses
    would be greatly appreciated.

  • Superb post but I was wondering if you could write a litte more on this topic?

    I’d be very grateful if you could elaborate a little
    bit further. Cheers!

  • Great post. I used to be checking continuously this weblog and
    I’m impressed! Extremely useful info particularly the last
    section 🙂 I take care of such information much. I was seeking this particular info
    for a very lengthy time. Thanks and good luck.

  • It is the best time to make a few plans for the long run and it is
    time to be happy. I’ve read this put up and if I may I desire to counsel you few fascinating issues or suggestions.
    Maybe you can write subsequent articles relating to this article.
    I wish to read more things about it!

  • Hi! I’ve been following your weblog for a long time now and finally got the bravery to go ahead
    and give you a shout out from Porter Tx! Just
    wanted to mention keep up the fantastic job!

  • I just like the helpful information you provide in your articles.
    I will bookmark your blog and take a look at again here regularly.
    I am moderately certain I will be told lots of new stuff proper right here!
    Best of luck for the next!

  • Every weekend i used to visit this web page, because
    i want enjoyment, for the reason that this this
    website conations genuinely pleasant funny
    material too.

  • The other day, while I was at work, my sister stole my apple ipad and tested to see if it can survive a thirty foot drop,
    just so she can be a youtube sensation. My apple ipad is now destroyed and she has 83 views.
    I know this is entirely off topic but I had to share it with someone!

  • You made some really good points there. I checked on the net for additional information about the issue and found most people
    will go along with your views on this website.

  • Ahaa, its fastidious discussion regarding this post at this place at this blog, I have read all that, so now me also commenting here.|

  • EPA Region 2 is hosting Brownfields Application Guidelines Workshops.
    The workshops are designed to assist local government and nonprofit organizations to better understand the application criteria and selection process for different EPA grants.
    Learn

  • I just want to mention I’m all new to weblog and honestly liked this web blog. Most likely I’m going to bookmark your blog . You certainly come with awesome well written articles. Regards for revealing your web site.

%d bloggers like this: