Anyone who has been surfing the web for a while is probably used to clicking through a CAPTCHA grid of street images, identifying everyday objects to prove that they’re a human and not an automated bot. Now, though, new research claims that locally run bots using specially trained image-recognition models can match human-level performance in this style of CAPTCHA, achieving a 100 percent success rate despite being decidedly not human.

ETH Zurich PhD student Andreas Plesner and his colleagues’ new research, available as a pre-print paper, focuses on Google’s ReCAPTCHA v2, which challenges users to identify which street images in a grid contain items like bicycles, crosswalks, mountains, stairs, or traffic lights. Google began phasing that system out years ago in favor of an “invisible” reCAPTCHA v3 that analyzes user interactions rather than offering an explicit challenge.

Despite this, the older reCAPTCHA v2 is still used by millions of websites. And even sites that use the updated reCAPTCHA v3 will sometimes use reCAPTCHA v2 as a fallback when the updated system gives a user a low “human” confidence rating.

  • Howdy
    link
    fedilink
    English
    963 months ago

    Need these bots as a browser addon now. When your using a VPN these things are the bane of your Internet browsing experience.

    • @[email protected]
      link
      fedilink
      English
      113 months ago

      The inverted Turing test, it would seem.

      Beep boop I am smarter than you… 🎵

      Bleep bloop you seem to me dumb as rock… 🎼

      img

  • @[email protected]
    link
    fedilink
    English
    303 months ago

    What’s ironic is that the main purpose of reCAPTCHA v2 is to train ML models. That’s why they show you blurry images of things you might see in traffic.

    AFAIK the way it works is that of the 9 images, something like 6 are images the system knows are True or False, and another 3 are ones it is being trained on. So, it shows you 9 images and says “tell me which images contain a motorcycle”. It uses the 6 it knows to determine whether or not to let you pass, and then uses your choices on the other 3 to train an ML model.

    Because of this, it takes me forever to get past reCAPTCHA v2, because I think it’s my duty to mistrain it as much as possible.

    • @[email protected]
      link
      fedilink
      English
      163 months ago

      You’re wasting your time. Your fingerprint is graded and discarded if you’re not reliable

      • @[email protected]
        link
        fedilink
        English
        33 months ago

        At least it adds noise to the system. It’s better than the people who are happily training the AI.

    • @[email protected]
      link
      fedilink
      English
      43 months ago

      I’m sure they use the reliability of your inputs for known images to determine whether to use your input to train unknown images.

  • @[email protected]
    link
    fedilink
    English
    213 months ago

    That’s good, hopefully we will quit seeing them. Because I’ve gotten to the point if I see a captcha I just go to another site unless it’s something I’ve got to do.

    • @cybersandwich
      link
      English
      63 months ago

      I literally couldn’t pass one for something I needed to access.

      I had to switch to the audio thing eventually and it took me multiple tries with that. I should just write a script that uses a fucking bot next time.

  • @_sideffect
    link
    English
    183 months ago

    Ok, so can we get rid of them then? They’re fucking annoying and waste time

  • @Godric
    link
    English
    153 months ago

    Mfw AI is better at proving they’re a human than I am

  • Jin
    link
    English
    143 months ago

    I need a bot because I get stuck in a loop of captchas

    • Echo Dot
      link
      fedilink
      English
      93 months ago

      It’s the age old question, does the pole count as part of a traffic light?

  • @ikidd
    link
    English
    133 months ago

    Then give me a FF addon that does these for me because I’m nowhere near that successful.

  • @psycho_driver
    link
    English
    113 months ago

    . . . that’s because we’ve been using these images to train AI for years?

  • @werefreeatlast
    link
    English
    73 months ago

    Recaptcha 4.0… what do you think about this image…an image of a kid riding their bike without any protective gear on a freeway.

    AI: a bike with a kid on it on a road. Perfectly fine.

    • Zoot
      link
      fedilink
      English
      43 months ago

      Emotion provoking images sounds like an ingenious solution honestly

        • @daddy32
          link
          English
          23 months ago

          “Let me tell you about my mother…”

      • @T156
        link
        English
        33 months ago

        It’d be a bit unreliable, though. Not everyone has the same reaction to the same thing, nor do they express it in a similar way.

        Someone might think a snake or a spider is cute, whereas another would want to incinerate it on the spot. A third might be concerned because they seem to be injured, etc.

        Not to mention that image recognition/emotional analysis has been an ongoing field of research for some time. Making the link is not overly difficult.

  • @Maggoty
    link
    English
    63 months ago

    Oh good we finally trained them enough. Can we please get rid of captcha now have the next portion?

  • @[email protected]
    link
    fedilink
    English
    53 months ago

    So the bots can now train the bots. About time. Now f off Google with your nasty privacy destroying captcha