3

Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning
Privacy concerns in client-server machine learning have given rise to private inference (PI), where neural inference occurs directly on …
Karthik Garimella, Nandan Kumar Jha, Brandon Reagen
PDF Cite Code Poster PPML Proceeding
Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning
CryptoNite: Revealing the Pitfalls of End-to-End Private Inference at Scale
In this paper we demonstrated that how the current trend in private inference myopically optimized the performance only for zero arrival rate; in particular, they have developed the mechanism to mitigate the bottlenecked caused by non-linearity in neural networks. However, in a real-world scenario when inference request comes even with a moderate arrival rate the homomorphic encryption becomes the main bottleneck since we can no longer pre-process it in the offline computation phase.
Karthik Garimella, Nandan Kumar Jha, Zahra Ghodsi, Siddharth Garg, Brandon Reagen
PDF Cite
CryptoNite: Revealing the Pitfalls of End-to-End Private Inference at Scale