Towards Fast and Scalable Private Inference

by   Jianqiao Mo, et al.

Privacy and security have rapidly emerged as first order design constraints. Users now demand more protection over who can see their data (confidentiality) as well as how it is used (control). Here, existing cryptographic techniques for security fall short: they secure data when stored or communicated but must decrypt it for computation. Fortunately, a new paradigm of computing exists, which we refer to as privacy-preserving computation (PPC). Emerging PPC technologies can be leveraged for secure outsourced computation or to enable two parties to compute without revealing either users' secret data. Despite their phenomenal potential to revolutionize user protection in the digital age, the realization has been limited due to exorbitant computational, communication, and storage overheads. This paper reviews recent efforts on addressing various PPC overheads using private inference (PI) in neural network as a motivating application. First, the problem and various technologies, including homomorphic encryption (HE), secret sharing (SS), garbled circuits (GCs), and oblivious transfer (OT), are introduced. Next, a characterization of their overheads when used to implement PI is covered. The characterization motivates the need for both GCs and HE accelerators. Then two solutions are presented: HAAC for accelerating GCs and RPU for accelerating HE. To conclude, results and effects are shown with a discussion on what future work is needed to overcome the remaining overheads of PI.


page 1

page 2

page 3

page 4


Revisiting Secure Computation Using Functional Encryption: Opportunities and Research Directions

Increasing incidents of security compromises and privacy leakage have ra...

Towards Secure and Practical Machine Learning via Secret Sharing and Random Permutation

With the increasing demands for privacy protection, privacy-preserving m...

Secret Sharing for Cloud Data Security

Cloud computing helps reduce costs, increase business agility and deploy...

Towards Scalable and Privacy-Preserving Deep Neural Network via Algorithmic-Cryptographic Co-design

Deep Neural Networks (DNNs) have achieved remarkable progress in various...

Characterizing and Optimizing End-to-End Systems for Private Inference

Increasing privacy concerns have given rise to Private Inference (PI). I...

SePEnTra: A secure and privacy-preserving energy trading mechanisms in transactive energy market

In this paper, we design and present a novel model called SePEnTra to en...

Secure Hybrid ITS Communication with Data Protection

In the future world of safe traffic, intelligent transportation systems ...

Please sign up or login with your details

Forgot password? Click here to reset