Timezone: »

 
Unsupervised Information Obfuscation for Split Inference of Neural Networks
Mohammad Samragh · Hossein Hosseini · Aleksei Triastcyn · Kambiz Azarian · Joseph B Soriaga · Farinaz Koushanfar

Splitting network computations between the edge device and a server enables low edge-compute inference of neural networks but might expose sensitive information about the test query to the server. To address this problem, existing techniques train the model to minimize information leakage for a given set of sensitive attributes. In practice, however, the test queries might contain attributes that are not foreseen during training. We propose instead an unsupervised obfuscation method to discard the information irrelevant to the main task. We formulate the problem via an information theoretical framework and derive an analytical solution for a given distortion to the model output. In our method, the edge device runs the model up to a split layer determined based on its computational capacity. It then obfuscates the obtained feature vector by removing the components in the null space of the next layer of the model as well as the low-energy components of the remaining signal. Our experimental results show that our method outperforms existing techniques in removing the information of the irrelevant attributes, reduces the communication cost, maintains the accuracy, and incurs only a small computational overhead.

Author Information

Mohammad Samragh (UC San Diego)
Hossein Hosseini (Qualcomm AI Research)
Aleksei Triastcyn (Qualcomm AI Research)
Kambiz Azarian (Qualcomm Inc.)
Joseph B Soriaga (Qualcomm Technologies, Inc.)
Farinaz Koushanfar (UCSD)

More from the Same Authors

  • 2021 : Contributed Talk #4 »
    Mohammad Samragh · Hossein Hosseini · Kambiz Azarian · Farinaz Koushanfar
  • 2021 Poster: Federated Learning of User Verification Models Without Sharing Embeddings »
    Hossein Hosseini · Hyunsin Park · Sungrack Yun · Christos Louizos · Joseph B Soriaga · Max Welling
  • 2021 Spotlight: Federated Learning of User Verification Models Without Sharing Embeddings »
    Hossein Hosseini · Hyunsin Park · Sungrack Yun · Christos Louizos · Joseph B Soriaga · Max Welling
  • 2020 : Lightning Talks Session 2 »
    Jichan Chung · Saurav Prakash · Mikhail Khodak · Ravi Rahman · Vaikkunth Mugunthan · xinwei zhang · Hossein Hosseini
  • 2019 : Poster Session 1 (all papers) »
    Matilde Gargiani · Yochai Zur · Chaim Baskin · Evgenii Zheltonozhskii · Liam Li · Ameet Talwalkar · Xuedong Shang · Harkirat Singh Behl · Atilim Gunes Baydin · Ivo Couckuyt · Tom Dhaene · Chieh Lin · Wei Wei · Min Sun · Orchid Majumder · Michele Donini · Yoshihiko Ozaki · Ryan P. Adams · Christian Geißler · Ping Luo · zhanglin peng · · Ruimao Zhang · John Langford · Rich Caruana · Debadeepta Dey · Charles Weill · Xavi Gonzalvo · Scott Yang · Scott Yak · Eugen Hotaj · Vladimir Macko · Mehryar Mohri · Corinna Cortes · Stefan Webb · Jonathan Chen · Martin Jankowiak · Noah Goodman · Aaron Klein · Frank Hutter · Mojan Javaheripi · Mohammad Samragh · Sungbin Lim · Taesup Kim · SUNGWOONG KIM · Michael Volpp · Iddo Drori · Yamuna Krishnamurthy · Kyunghyun Cho · Stanislaw Jastrzebski · Quentin de Laroussilhe · Mingxing Tan · Xiao Ma · Neil Houlsby · Andrea Gesmundo · Zalán Borsos · Krzysztof Maziarz · Felipe Petroski Such · Joel Lehman · Kenneth Stanley · Jeff Clune · Pieter Gijsbers · Joaquin Vanschoren · Felix Mohr · Eyke Hüllermeier · Zheng Xiong · Wenpeng Zhang · wenwu zhu · Weijia Shao · Aleksandra Faust · Michal Valko · Michael Y Li · Hugo Jair Escalante · Marcel Wever · Andrey Khorlin · Tara Javidi · Anthony Francis · Saurajit Mukherjee · Jungtaek Kim · Michael McCourt · Saehoon Kim · Tackgeun You · Seungjin Choi · Nicolas Knudde · Alexander Tornede · Ghassen Jerfel