Stories
Slash Boxes
Comments

SoylentNews is people

posted by janrinok on Friday May 06 2022, @10:14PM   Printer-friendly

New method detects deepfake videos with up to 99% accuracy:

Computer scientists at UC Riverside can detect manipulated facial expressions in deepfake videos with higher accuracy than current state-of-the-art methods. The method also works as well as current methods in cases where the facial identity, but not the expression, has been swapped, leading to a generalized approach to detect any kind of facial manipulation. The achievement brings researchers a step closer to developing automated tools for detecting manipulated videos that contain propaganda or misinformation.

Developments in video editing software have made it easy to exchange the face of one person for another and alter the expressions on original faces. As unscrupulous leaders and individuals deploy manipulated videos to sway political or social opinions, the ability to identify these videos is considered by many essential to protecting free democracies. Methods exist that can detect with reasonable accuracy when faces have been swapped. But identifying faces where only the expressions have been changed is more difficult and to date, no reliable technique exists.

[...] The UC Riverside method divides the task into two components within a deep neural network. The first branch discerns facial expressions and feeds information about the regions that contain the expression, such as the mouth, eyes, or forehead, into a second branch, known as an encoder-decoder. The encoder-decoder architecture is responsible for manipulation detection and localization.

More information: Ghazal Mazaheri, Amit K. Roy-Chowdhury, Detection and Localization of Facial Expression Manipulations. arXiv:2103.08134v1 [cs.CV], arxiv.org/abs/2103.08134


Original Submission

This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
(1)
  • (Score: 2, Insightful) by MIRV888 on Friday May 06 2022, @10:39PM (9 children)

    by MIRV888 (11376) on Friday May 06 2022, @10:39PM (#1242886)

    Sciencey words are not going to convince the unwashed masses. It is a question of what news outlets people trust.
    Unfortunately we are in deep sh1t on that level.

    • (Score: 3, Insightful) by Anonymous Coward on Friday May 06 2022, @11:17PM (8 children)

      by Anonymous Coward on Friday May 06 2022, @11:17PM (#1242892)

      Don't worry, friend. The deepfake makers will use this detector to improve their deepfakes.

      • (Score: 4, Insightful) by Opportunist on Friday May 06 2022, @11:47PM (7 children)

        by Opportunist (5545) on Friday May 06 2022, @11:47PM (#1242899)

        What for? Have you seen just what harebrained bullshit some people believe? Why bother improving your lies when the crappy and cheap ones are absolutely sufficient?

        • (Score: 0) by Anonymous Coward on Saturday May 07 2022, @12:49AM (5 children)

          by Anonymous Coward on Saturday May 07 2022, @12:49AM (#1242908)

          If the detection rate is close to 100%, the social media giants can flag or delete the videos automatically. If the detection rate craters due to deepfake improvements, the videos can survive and spread.

          • (Score: 4, Insightful) by maxwell demon on Saturday May 07 2022, @04:42AM (3 children)

            by maxwell demon (1608) Subscriber Badge on Saturday May 07 2022, @04:42AM (#1242931) Journal

            Not only that, they even will have added credibility, since they all passed that filter.

            --
            The Tao of math: The numbers you can count are not the real numbers.
            • (Score: -1, Spam) by Anonymous Coward on Saturday May 07 2022, @07:50AM (2 children)

              by Anonymous Coward on Saturday May 07 2022, @07:50AM (#1242947)

              99% is certainly way beyond janrinok's 16.37% success rate on aristarchus detection. Just sayin', please don't Spam Mod me, bro!!

              • (Score: -1, Spam) by Anonymous Coward on Saturday May 07 2022, @09:08AM (1 child)

                by Anonymous Coward on Saturday May 07 2022, @09:08AM (#1242955)

                Make that 14.897%. (Incorrect Spam mod thrown in anger and error) janrinok fails again. So sad. And Runaway rages in the blood of her second mending fantasies. Really sad.

                • (Score: 0) by adamantine on Sunday May 08 2022, @07:17AM

                  by adamantine (17130) on Sunday May 08 2022, @07:17AM (#1243142)

                  And now the specificity is down around 9.36%? Repeated iterations of false guesses results in lower accuracy. We should know this from Runaway's days at the range. But, I, personally, do not know. Keep Calm, and janrinok on, I say.

          • (Score: 2) by Opportunist on Saturday May 07 2022, @09:47AM

            by Opportunist (5545) on Saturday May 07 2022, @09:47AM (#1242961)

            So flag it, all that does is make it more credible to the rabbit hole enthusiasts because "the man" wants to slander "truths".

        • (Score: 2) by Michael on Saturday May 07 2022, @08:25PM

          by Michael (7157) on Saturday May 07 2022, @08:25PM (#1243059)

          "Shallowfakes"

  • (Score: 5, Insightful) by DannyB on Saturday May 07 2022, @12:06AM (6 children)

    by DannyB (5839) Subscriber Badge on Saturday May 07 2022, @12:06AM (#1242902) Journal

    1. Deep fakes

    2. 99% accurate deep fake detector

    3. New deep fakes, trained using item (2) so that they are 99% likely NOT to be detected as deep fakes.

    4. GOSUB 2.

    --
    How often should I have my memory checked? I used to know but...
    • (Score: 0) by Anonymous Coward on Saturday May 07 2022, @12:58AM

      by Anonymous Coward on Saturday May 07 2022, @12:58AM (#1242911)

      proving the news reader was fake, does not do anything about the news itself.

    • (Score: 4, Touché) by Anonymous Coward on Saturday May 07 2022, @02:01AM (4 children)

      by Anonymous Coward on Saturday May 07 2022, @02:01AM (#1242917)

      deep fakes
      deep deep fakes
      deep deep deep fakes
      deep deep deep deep fakes
      deep deep deep deep deep *** STACK OVERFLOW ***

      • (Score: 2) by Mojibake Tengu on Saturday May 07 2022, @02:44AM (3 children)

        by Mojibake Tengu (8598) on Saturday May 07 2022, @02:44AM (#1242923) Journal

        Modded informative because parent is so much pre-conditioned by scholar dogmatic hypnotic framing to hate GOTO so much that he improperly wrote GOSUB instead.

        --
        The edge of 太玄 cannot be defined, for it is beyond every aspect of design
        • (Score: 0) by Anonymous Coward on Saturday May 07 2022, @11:13AM (1 child)

          by Anonymous Coward on Saturday May 07 2022, @11:13AM (#1242970)

          Well, in practice, this is an infinite loop.

          ( We are screwed. )

          • (Score: 1, Informative) by Anonymous Coward on Sunday May 08 2022, @02:47PM

            by Anonymous Coward on Sunday May 08 2022, @02:47PM (#1243193)

            GOTO would be an infinite loop. GOSUB will eventually crash out due to depth of recursion.

        • (Score: 2) by DannyB on Sunday May 08 2022, @08:46PM

          by DannyB (5839) Subscriber Badge on Sunday May 08 2022, @08:46PM (#1243280) Journal

          By 1980 it was frowned upon to use GOTO. Languages should not even have GOTO. So the next bestest thing is to use GOSUB. What could go wrong?

          --
          How often should I have my memory checked? I used to know but...
  • (Score: 0) by Anonymous Coward on Saturday May 07 2022, @01:48AM

    by Anonymous Coward on Saturday May 07 2022, @01:48AM (#1242915)

    For those of us shallow nerds.

    Come on, don't discriminate - we may be shallow, but we still nerds.

  • (Score: -1, Offtopic) by Anonymous Coward on Saturday May 07 2022, @02:29AM

    by Anonymous Coward on Saturday May 07 2022, @02:29AM (#1242922)

    Yo, I'll tell you what I want, what I really really want,
    So tell me what you want, what you really really want,
    I'll tell you what I want, what I really really want,
    So tell me what you want, what you really really want,
    I wanna, I wanna, I wanna ha, I wanna ha, I wanna really
    Really really wanna zigazig ah.

    If you want my future forget my past,
    If you wanna get with me better make it fast,
    Now don't go wasting, my precious time,
    Get your act together we can be just fine.

    I'll tell you what I want, what I really really want,
    So tell me what you want, what you really really want,
    I wanna ha, I wanna ha, I wanna ha, I wanna ha, I wanna really
    Really really wanna zigazang ah.

    If you wanna be my lover, you gotta get with my friends,(gottagetwithmyfriends!)
    Make it last forever friendship never ends,
    If you wanna be my lover, you have got to give,
    Taking is too easy, but that's the way it is.

    So what you think about that? Now you know how I feel.
    Say you can handle my love are you for real,(are you for real)
    I won't be hasty, I'll give you a try
    If you really bug me then I'll say goodbye.

    Yo I'll tell you what I want, what I really really want,
    So tell me what you want, what you really really want,
    I wanna ha, I wanna ha, I wanna ha I wanna ha, I wanna really
    Really really wanna zigazig ah.

    If you wanna be my lover, you gotta get with my friends,
    Make it last forever friendship never ends,
    If you wanna be my lover, you have got to give,
    Taking is too easy, but that's the way it is.

    So here's a story from A to Z, you wanna get with me
    You gotta listen carefully,
    We got Em in the place who likes it in your face,
    We got G like mc who likes it on an
    Easy V doesn't come for free, shes a real lady
    And as for me.. Ha you'll see.
    Slam your body down and wind it all around
    Slam your body down and wind it all around.

    If you wanna be my lover, you gotta get with my friends,
    Make it last forever friendship never ends,
    If you wanna be my lover, you have got to give,
    Taking is too easy, but that's the way it is.

    If you wanna be my lover, you gotta, you gotta, you
    Gotta,
    You gotta, you gotta!!!!! Make it last forever (stomp! Stomp! Stomp! Stomp!)
    Slam your body down and wind it all around?
    Slam your body down and wind it all around.(ha ha ha ha)
    Slam your body down and wind it all around.
    Slam your body down zigazig ah

    If you wanna be my lover!(lover! Lover lover lover!)

(1)