Summary of Linearizing Models For Efficient Yet Robust Private Inference, by Sreetama Sarkar et al.
Linearizing Models for Efficient yet Robust Private Inference
by Sreetama Sarkar, Souvik Kundu, Peter A. Beerel
First submitted to arxiv on: 8 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes RLNet, a class of robust linearized networks that can improve latency efficiency and model performance for private inference (PI) frameworks in client-server applications. By reducing the number of high-latency ReLU operations, RLNet models achieve a “triple win ticket” of improved classification accuracy on clean, naturally perturbed, and gradient-based perturbed images using a shared-mask shared-weight architecture. The authors demonstrate the efficacy of RLNet through extensive experiments with ResNet and WRN model variants on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making computer models that can keep data private while also working well in different environments. Right now, these models are slow because they need to be very secure. The researchers created a new kind of model called RLNet that can work faster and still keep the data safe. They tested it with some popular images datasets and showed that it works better than other similar models. |
Keywords
* Artificial intelligence * Classification * Inference * Mask * Relu * Resnet
