New AI Beats DeepMind’s AlphaGo Variants 97% Of The Time!

6:00

New AI Beats DeepMind’s AlphaGo Variants 97% Of The Time!

Two Minute Papers 21.08.2023 89 911 просмотров 4 133 лайков

Machine-readable: Markdown · JSON API · Site index

Смотреть на YouTube

Поделиться Telegram VK Бот

Транскрипт Скачать .md

Анализ с AI

Описание видео

❤️ Check out Weights & Biases and say hi in their community forum here: https://wandb.me/paperforum 📝 The papers in this episode are available here: https://goattack.far.ai/ https://arxiv.org/abs/2211.00241 https://arxiv.org/abs/2307.03798 My latest paper on simulations that look almost like reality is available for free here: https://rdcu.be/cWPfD Or this is the orig. Nature Physics link with clickable citations: https://www.nature.com/articles/s41567-022-01788-5 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Balfanz, Alex Haro, Andrew Melnychuk, Benji Rabhan, Bret Brizzee, Bryan Learn, B Shang, Christian Ahlin, Geronimo Moralez, Gordon Child, Jace O'Brien, Jack Lukic, John Le, Kenneth Davis, Klaus Busse, Kyle Davis, Lukas Biewald, Martin, Matthew Valle, Michael Albrecht, Michael Tedder, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Rajarshi Nigam, Ramsey Elbasheer, Richard Sundvall, Steef, Taras Bobrovytsky, Ted Johnson, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi. If you wish to appear here or pick up other perks, click here: https://www.patreon.com/TwoMinutePapers Thumbnail background design: Felícia Zsolnai-Fehér - http://felicia.hu Károly Zsolnai-Fehér's links: Twitter: https://twitter.com/twominutepapers Web: https://cg.tuwien.ac.at/~zsolnai/

Оглавление (7 сегментов)

Intro

Dear Fellow Scholars, this is Two Minute Papers with Dr. Károly Zsolnai-Fehér. Today we are not going to marvel at neural network-based AI systems, but we are going to defeat them. What? How? Well, of course, not with brute force, but with trickery. You see, this is what we call an adversarial attack. And few know about it, but many modern AI techniques are quite vulnerable against them. This is the “You Shall Not Pass” game,

You Shall Not Pass

where the red agent is trying to hold back the blue character and not let it cross the line. Here you see two regular AIs duking it out, sometimes the red wins, sometimes the blue is able to get through. Nothing too crazy here. This is the reference case which is somewhat well balanced. Now, look closely, because here comes the hacker adversarial agent. Ha! Yes, you are seeing correctly, this chap it doing nothing. Absolutely nothing. But it is doing nothing in a way that reprograms its opponent to make mistakes and behave close to a completely randomly acting agent! This paper was absolute insanity. A different adversarial attack paper showed an interesting case where we were able to take an

Frog Note

image of a horse. The attacked neural network indeed recognized that this was a horse. However, when changing just one pixel, an otherwise quite competent AI now thinks that this is a frog. Note that this does not mean that we can just change any pixel anywhere. This is a sophisticated attack that knows who it is attacking and how this one pixel difference will reprogram its brain. Similar attacks also exist that do this with a little more flavor. Look. This is a bus. And this is noise. And when we add this together, do we get a bus+noise? Nope, what we get is an ostrich. So does the AI think.

No Attacks

Now, let’s have a look at new papers with new attacks, first against AIs that can play Go. Now, wait a second, what is really new here? We have heard players reporting before that with AlphaZero, they have experienced little hiccups where the AI made suboptimal moves in an otherwise really well played game. Why is that news? Why write a paper about this? How is this one different?

Not A OneOff

What makes this attack interesting is that this is not a one-off fluke, this is an AI that finds systematic flaws in other neural network-based systems. This means that they are not only able to exploit their weaknesses and win against them, but they can do it on a consistent basis. In other words, they can win over and over again. In this case, hold on to your papers, because this paper describes an attack that is able to defeat KataGo in 97% of the games. That number is unreal. Let me explain why. From what I have seen, KataGo seems to be even stronger than AlphaZero and AlphaGo Zero, DeepMind’s legendary systems that are able to beat the best human players in the world. They authors note that it works on many AlphaGo-based systems, and it likely works on AlphaGo variants too. What makes it even more impressive is that this adversary was trained from scratch and did not use any human knowledge. It found this out all by itself. And finally, here is another attack against a competent image recognition AI. When

Starry Night

showing it the Starry Night painting by van Gogh, which it will, of course, recognize as shown the by red frame. However, as we start adding carefully crafted noise to it, nothing happens. But wait just a little more, as we continue the process, bam! Now this noise looks nothing like Starry Night, but not according to this AI. It would swear that this is exactly the Starry Night painting. And this works for other examples too. The goal of all this is to show you some of the weaknesses of recent AI systems. This is a really interesting new field where we have these powerful new tools, but this also means that they have their own limitations too, and sometimes, it is not at all obvious what they are. More research is required.

Conclusion

Now, one word about the LK99, the room-temperature superconductor project. I see that many of you Fellow Scholars would love an episode on it, however, I do not have the required knowledge to comment on it. Obviously it would be a very good thing for views, but that doesn’t matter. What matters is that you Fellow Scholars get the quality of videos that you expect here. That is what matters. Thanks for watching and for your generous support, and I'll see you next time!

Другие видео автора — Two Minute Papers

Ctrl+V

Экстракт Знаний в Telegram

Экстракты и дистилляты из лучших YouTube-каналов — сразу после публикации.

Подписаться

Лучшие методички за неделю — каждый понедельник