Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-003-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-003-alpha.b-cdn.net
      • sl-yoda-v2-stream-003-beta.b-cdn.net
      • 1544410162.rsc.cdn77.org
      • 1005514182.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
            Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders

            Dec 10, 2023

            Speakers

            JD

            Jan Dubiński

            Speaker · 0 followers

            SP

            Stanisław Pawlak

            Speaker · 0 followers

            FB

            Franziska Boenisch

            Speaker · 0 followers

            About

            Machine Learning as a Service (MLaaS) APIs provide ready-to-use and high-utility encoders that generate vector representations for given inputs. Since these encoders are very costly to train, they become lucrative targets for model stealing attacks during which an adversary leverages query access to the API to replicate the encoder locally at a fraction of the original training costs. We propose *Bucks for Buckets (B4B)*, the first *active defense* that prevents stealing while the attack is happ…

            Organizer

            N2
            N2

            NeurIPS 2023

            Account · 624 followers

            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

            An Information Theory Perspective on Variance-Invariance-Covariance Regularization
            04:46

            An Information Theory Perspective on Variance-Invariance-Covariance Regularization

            Ravid Shwartz-Ziv, …

            N2
            N2
            NeurIPS 2023 16 months ago

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

            Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation
            04:55

            Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation

            Xin Yuan, …

            N2
            N2
            NeurIPS 2023 16 months ago

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

            One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
            04:41

            One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization

            Minghua Liu, …

            N2
            N2
            NeurIPS 2023 16 months ago

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

            Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions
            04:56

            Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions

            Duligur Ibeling, …

            N2
            N2
            NeurIPS 2023 16 months ago

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

            BanditPAM++: Faster k-medoids Clustering
            04:38

            BanditPAM++: Faster k-medoids Clustering

            Mo Tiwari, …

            N2
            N2
            NeurIPS 2023 16 months ago

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

            MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling
            07:33

            MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling

            Kelvin Lee, …

            N2
            N2
            NeurIPS 2023 15 months ago

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

            Interested in talks like this? Follow NeurIPS 2023