Collaborative inference has recently emerged as an intriguing framework for
applying deep learning to Internet of Things (IoT) applications, which works by
splitting a DNN model into two subpart models respectively on
resource-constrained IoT devices and the cloud. Even though IoT applications’
raw input data is not directly exposed to the cloud in such framework,
revealing the local-part model’s intermediate output still entails privacy
risks. For mitigation of privacy risks, differential privacy could be adopted
in principle. However, the practicality of differential privacy for
collaborative inference under various conditions remains unclear. For example,
it is unclear how the calibration of the privacy budget epsilon will affect the
protection strength and model accuracy in presence of the state-of-the-art
reconstruction attack targeting collaborative inference, and whether a good
privacy-utility balance exists. In this paper, we provide the first systematic
study to assess the effectiveness of differential privacy for protecting
collaborative inference in presence of the reconstruction attack, through
extensive empirical evaluations on various datasets. Our results show
differential privacy can be used for collaborative inference when confronted
with the reconstruction attack, with insights provided about privacyutility
trade-offs. Specifically, across the evaluated datasets, we observe there
exists a suitable privacy budget range (particularly 100<=epsilon<=200 in our
evaluation) providing a good tradeoff between utility and privacy protection.
Our key observation drawn from our study is that differential privacy tends to
perform better in collaborative inference for datasets with smaller intraclass
variations, which, to our knowledge, is the first easy-toadopt practical

Go to Source of this post
Author Of this post: <a href="">Jihyeon Ryu</a>, <a href="">Yifeng Zheng</a>, <a href="">Yansong Gao</a>, <a href="">Sharif Abuadbba</a>, <a href="">Junyaup Kim</a>, <a href="">Dongho Won</a>, <a href="">Surya Nepal</a>, <a href="">Hyoungshick Kim</a>, <a href="">Cong Wang</a>

By admin