Timezone: »

 
Differentially Private CutMix for Split Learning with Vision Transformer
Seungeun Oh · Jihong Park · Sihun Baek · Hyelin Nam · Praneeth Vepakomma · Ramesh Raskar · Mehdi Bennis · Seong-Lyun Kim
Event URL: https://openreview.net/forum?id=gRCWdltNQq »

Recently, vision transformer (ViT) has started to outpace the conventional CNN in computer vision tasks. Considering privacy-preserving distributed learning with ViT, federated learning (FL) communicates models, which becomes ill-suited due to ViT's large model size and computing costs. Split learning (SL) detours this by communicating smashed data at a cut-layer, yet suffers from data privacy leakage and large communication costs caused by high similarity between ViT's smashed data and input data. Motivated by this problem, we propose \textit{DP-CutMixSL}, a differentially private (DP) SL framework by developing \textit{DP patch-level randomized CutMix (DP-CutMix)}, a novel privacy-preserving inter-client interpolation scheme that removes randomly selected patches in smashed data. By experiment, we show that DP-CutMixSL not only boosts privacy guarantees and communication efficiency, but also achieves higher accuracy than its Vanilla SL counterpart. Theoretically, we analyze that DP-CutMix amplifies R\'enyi DP (RDP), which is upper-bounded by its Vanilla Mixup counterpart.

Author Information

Seungeun Oh (Yonsei University)
Jihong Park (Deakin University)
Sihun Baek (Yonsei University)
Hyelin Nam
Praneeth Vepakomma (MIT)
Ramesh Raskar (Massachusetts Institute of Technology)
Mehdi Bennis (University of Oulu)
Seong-Lyun Kim (Yonsei University)

More from the Same Authors

  • 2020 : DAMS: Meta-estimation of private sketch data structures for differentially private contact tracing »
    Praneeth Vepakomma
  • 2022 Workshop: Federated Learning: Recent Advances and New Challenges »
    Shiqiang Wang · Nathalie Baracaldo · Olivia Choudhury · Gauri Joshi · Peter Richtarik · Praneeth Vepakomma · Han Yu
  • 2019 : Poster Session »
    Nathalie Baracaldo · Seth Neel · Tuyen Le · Dan Philps · Suheng Tao · Sotirios Chatzis · Toyo Suzumura · Wei Wang · WENHANG BAO · Solon Barocas · Manish Raghavan · Samuel Maina · Reginald Bryant · Kush Varshney · Skyler D. Speakman · Navdeep Gill · Nicholas Schmidt · Kevin Compher · Naveen Sundar Govindarajulu · Vivek Sharma · Praneeth Vepakomma · Tristan Swedish · Jayashree Kalpathy-Cramer · Ramesh Raskar · Shihao Zheng · Mykola Pechenizkiy · Marco Schreyer · Li Ling · Chirag Nagpal · Robert Tillman · Manuela Veloso · Hanjie Chen · Xintong Wang · Michael Wellman · Matthew van Adelsberg · Ben Wood · Hans Buehler · Mahmoud Mahfouz · Antonios Alexos · Megan Shearer · Antigoni Polychroniadou · Lucia Larise Stavarache · Dmitry Efimov · Johnston P Hall · Yukun Zhang · Emily Diana · Sumitra Ganesh · Vineeth Ravi · · Swetasudha Panda · Xavier Renard · Matthew Jagielski · Yonadav Shavit · Joshua Williams · Haoran Wei · Shuang (Sophie) Zhai · Xinyi Li · Hongda Shen · Daiki Matsunaga · Jaesik Choi · Alexis Laignelet · Batuhan Guler · Jacobo Roa Vicens · Ajit Desai · Jonathan Aigrain · Robert Samoilescu
  • 2019 : Poster session »
    Michael Melese Woldeyohannis · Bernardt Duvenhage · Nyamos Waigama · Asaye Bir Senay · Claire Babirye · Tensaye Ayalew · Kelechi Ogueji · Vinay Prabhu · Prabu Ravindran · Fadilulah Wahab · ChukwuNonso H Nwokoye · Paul Duckworth · Hafte Abera · Abebe Mideksa · Loubna Benabbou · Anugraha Sinha · Ivan Kiskin · Robert Soden · Tupokigwe Isagah · Rehema Mwawado · Yimer Mohammed · Bryan Wilder · Daniel Omeiza · Sunayana Rane · Richard Mgaya · Samsun Knight · Jessenia Gonzalez Villarreal · Eyob Beyene · Monika Obrocka Tulinska · Luis Fernando Cantu Diaz de Leon · Joseph Aro · Michael T Smith · Michael Famoroti · Praneeth Vepakomma · Ramesh Raskar · Debjani Bhowmick · Chukwunonso H Nwokoye · Alejandro Noriega Campero · Hope Mbelwa · Anusua Trivedi