Unsupervised Information Obfuscation for Split Inference of Neural Networks

by   Mohammad Samragh, et al.

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 based on the first layer of the server model by removing the components in the null space 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 and maintaining the accuracy on the target label. We also show that our method reduces the communication cost and incurs only a small computational overhead.


page 1

page 2

page 3

page 4


Communication-Computation Trade-Off in Resource-Constrained Edge Inference

The recent breakthrough in artificial intelligence (AI), especially deep...

Multi-limb Split Learning for Tumor Classification on Vertically Distributed Data

Brain tumors are one of the life-threatening forms of cancer. Previous s...

SC2: Supervised Compression for Split Computing

Split computing distributes the execution of a neural network (e.g., for...

Optimal Model Placement and Online Model Splitting for Device-Edge Co-Inference

Device-edge co-inference opens up new possibilities for resource-constra...

A Bargaining Game for Personalized, Energy Efficient Split Learning over Wireless Networks

Split learning (SL) is an emergent distributed learning framework which ...

Communication and Computation Reduction for Split Learning using Asynchronous Training

Split learning is a promising privacy-preserving distributed learning sc...

Progressive Feature Transmission for Split Inference at the Wireless Edge

In edge inference, an edge server provides remote-inference services to ...

Please sign up or login with your details

Forgot password? Click here to reset