Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Dimension-independent Certified Neural Network Watermarks via Mollifier Smoothing
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-002-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-002-alpha.b-cdn.net
      • sl-yoda-v2-stream-002-beta.b-cdn.net
      • 1001562353.rsc.cdn77.org
      • 1075090661.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
            Dimension-independent Certified Neural Network Watermarks via Mollifier Smoothing
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Dimension-independent Certified Neural Network Watermarks via Mollifier Smoothing

            Jul 24, 2023

            Sprecher:innen

            JR

            Jiaxiang Ren

            Sprecher:in · 0 Follower:innen

            YZ

            Yang Zhou

            Sprecher:in · 0 Follower:innen

            JJ

            Jiayin Jin

            Sprecher:in · 0 Follower:innen

            Über

            Certified_Watermarks is the first to provide a watermark certificate against l_2-norm watermark removal attacks, by leveraging the randomized smoothing techniques for certified robustness to adversarial attacks. However, the randomized smoothing techniques suffer from hardness of certified robustness in high-dimensional space against l_p-norm attacks for large p (p>2). The certified watermark method based on the randomized smoothing is no exception, i.e., fails to provide meaningful certific…

            Organisator

            I2
            I2

            ICML 2023

            Konto · 657 Follower:innen

            Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!

            Professionelle Aufzeichnung und Livestreaming – weltweit.

            Freigeben

            Empfohlene Videos

            Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind

            Neuro-Symbolic Dialogue Management using Prompt-Based Transfer Learning for Dialogue Act Controlled Open-Domain NLG
            44:43

            Neuro-Symbolic Dialogue Management using Prompt-Based Transfer Learning for Dialogue Act Controlled Open-Domain NLG

            Marilyn Walker

            I2
            I2
            ICML 2023 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Knowledge Hypergraph Embedding Meets Relational Algebra
            05:17

            Knowledge Hypergraph Embedding Meets Relational Algebra

            Bahare Fatemi, …

            I2
            I2
            ICML 2023 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Feature Learning in Deep Classifiers Through Intermediate Neural Collapse
            05:35

            Feature Learning in Deep Classifiers Through Intermediate Neural Collapse

            Akshay Rangamani, …

            I2
            I2
            ICML 2023 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Divide and Conquer Dynamic Programming: An Almost Linear Time Change Point Detection Methodology in High Dimensions
            04:34

            Divide and Conquer Dynamic Programming: An Almost Linear Time Change Point Detection Methodology in High Dimensions

            Daren Wang, …

            I2
            I2
            ICML 2023 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            PyTorch 2.x: Faster, More Pythonic, and as Dynamic as Ever
            24:01

            PyTorch 2.x: Faster, More Pythonic, and as Dynamic as Ever

            Natalia Gimelshein

            I2
            I2
            ICML 2023 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Evaluating Self-Supervised Learning via Risk Decomposition
            08:32

            Evaluating Self-Supervised Learning via Risk Decomposition

            Yann Dubois, …

            I2
            I2
            ICML 2023 2 years ago

            Ewigspeicher-Fortschrittswert: 0 = 0.0%

            Interessiert an Vorträgen wie diesem? ICML 2023 folgen