Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Amplifying Membership Exposure via Data Poisoning
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-009-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-009-alpha.b-cdn.net
      • sl-yoda-v2-stream-009-beta.b-cdn.net
      • 1766500541.rsc.cdn77.org
      • 1441886916.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
            Amplifying Membership Exposure via Data Poisoning
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Amplifying Membership Exposure via Data Poisoning

            Nov 28, 2022

            Speakers

            YC

            Yufei Chen

            Speaker · 0 followers

            CS

            Chao Shen

            Speaker · 0 followers

            YS

            Yun Shen

            Speaker · 0 followers

            About

            As in-the-wild data are increasingly involved in the training stage, machine learning applications become more susceptible to data poisoning attacks. Such attacks typically lead to test-time accuracy degradation or controlled misprediction. In this paper, we investigate the third type of exploitation of data poisoning - increasing the risks of privacy leakage of benign training samples. To this end, we demonstrate a set of data poisoning attacks to amplify the membership exposure of the targeted…

            Organizer

            N2
            N2

            NeurIPS 2022

            Account · 952 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

            Phase transitions in when feedback is useful
            04:59

            Phase transitions in when feedback is useful

            Lokesh Boominathan, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Don't Waste Data: Transfer Learning to Leverage All Data for Machine-Learnt Climate Model Emulation
            09:10

            Don't Waste Data: Transfer Learning to Leverage All Data for Machine-Learnt Climate Model Emulation

            Raghul Parthipan, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            GlanceNets: Interpretabile, Leak-proof Concept-based Models
            04:23

            GlanceNets: Interpretabile, Leak-proof Concept-based Models

            Emanuele Marconato, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            QUARK: Controllable Text Generation with Reinforced UNlearning
            04:40

            QUARK: Controllable Text Generation with Reinforced UNlearning

            Ximing Lu, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning
            05:18

            In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning

            Jiaqi Wang, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions
            16:55

            InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions

            Bodhisattwa Prasad Majumder, …

            N2
            N2
            NeurIPS 2022 2 years ago

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

            Interested in talks like this? Follow NeurIPS 2022