Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Online Adversarial Purification based on Self-supervised Learning
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-013-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-013-alpha.b-cdn.net
      • sl-yoda-v3-stream-013-beta.b-cdn.net
      • 1668715672.rsc.cdn77.org
      • 1420896597.rsc.cdn77.org
      • Subtitles
      • Off
      • English
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Online Adversarial Purification based on Self-supervised Learning
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Online Adversarial Purification based on Self-supervised Learning

            May 3, 2021

            Speakers

            CS

            Changhao Shi

            Speaker · 0 followers

            CH

            Chester Holtz

            Speaker · 0 followers

            GM

            Gal Mishne

            Speaker · 0 followers

            About

            Deep neural networks are known to be vulnerable to adversarial examples, where a perturbation in the input space leads to an amplified shift in the latent network representation. In this paper, we combine canonical supervised learning with self-supervised representation learning, and present Self-supervised Online Adversarial Purification (SOAP), a novel defense strategy that uses a self-supervised loss to purify adversarial examples at test-time. Our approach leverages the label-independent nat…

            Organizer

            I2
            I2

            ICLR 2021

            Account · 901 followers

            About ICLR 2021

            The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.

            Like the format? Trust SlidesLive to capture your next event!

            Professional recording and live streaming, delivered globally.

            Sharing

            Recommended Videos

            Presentations on similar topic, category or speaker

            Understanding the effects of data parallelism and sparsity on neural network training
            04:52

            Understanding the effects of data parallelism and sparsity on neural network training

            Namhoon Lee, …

            I2
            I2
            ICLR 2021 4 years ago

            Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%

            Can we learn from Psychology's reproducibility crisis?
            20:33

            Can we learn from Psychology's reproducibility crisis?

            Samuel J. Bell

            I2
            I2
            ICLR 2021 4 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
            07:30

            Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels

            Denis Yarats, …

            I2
            I2
            ICLR 2021 4 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Extreme Memorization via Scale of Initialization
            05:08

            Extreme Memorization via Scale of Initialization

            Harsh Mehta, …

            I2
            I2
            ICLR 2021 4 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Human-Level Performance in No-Press Diplomacy via Equilibrium Search
            15:10

            Human-Level Performance in No-Press Diplomacy via Equilibrium Search

            Jonathan Gray, …

            I2
            I2
            ICLR 2021 4 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            AI4SCIENCE: A REVOLUTION IN THE MAKING
            27:10

            AI4SCIENCE: A REVOLUTION IN THE MAKING

            Anima Anandkumar

            I2
            I2
            ICLR 2021 4 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Interested in talks like this? Follow ICLR 2021