Open in app

Sign In

Write

Sign In

Daniel Huynh
Daniel Huynh

175 Followers

Home

About

Published in Mithril Security

·May 26, 2021

Our vision at Mithril Security: make AI private again

Our vision at Mithril Security These last years we have seen the enormous progress made by AI algorithms. Computer vision has been dominated these last years by deep learning, showing excellent performances on very diverse tasks ranging from radiography analysis to biometric identification. …

AI

4 min read

Our vision at Mithril Security : make AI private again
Our vision at Mithril Security : make AI private again
AI

4 min read


May 19, 2021

Confidential computing explained. Part 2 : attestation

Confidential computing explained: Part 1 : introduction Part 2 : attestation I — Introduction We saw in the previous article why we need techniques such as confidential computing to secure sensitive workloads, and how different it is from regular methods.

Privacy

6 min read

Confidential computing explained. Part 2 : attestation
Confidential computing explained. Part 2 : attestation
Privacy

6 min read


Apr 27, 2021

Confidential computing explained. Part 1 : introduction

Confidential computing explained: Part 1 : introduction Part 2 : attestation I — Introduction

Privacy

7 min read

Confidential computing explained. Part 1 : introduction
Confidential computing explained. Part 1 : introduction
Privacy

7 min read


Published in Towards Data Science

·Jun 26, 2020

Homomorphic Encryption intro: Part 3: Encoding and decoding in CKKS

EDIT: This post is now available on OpenMined’s blog. Due to issues to write code and maths, I have decided to release the rest of the series on OpenMined for a more comfortable reader experience. Links are available here: CKKS Explained: Part 1, Vanilla Encoding and Decoding CKKS Explained: Part…

Homomorphic Encryption

4 min read

Homomorphic Encryption intro: Part 3: Encoding and decoding in CKKS
Homomorphic Encryption intro: Part 3: Encoding and decoding in CKKS
Homomorphic Encryption

4 min read


Published in Towards Data Science

·Jun 22, 2020

Homomorphic Encryption intro: Part 2: HE landscape and CKKS

Description of the Homomorphic Encryption landscape, what is HE and a first look at CKKS for an HE scheme on complex numbers. — Homomorphic encryption intro: Part 1: Overview and use cases Part 2: HE landscape and CKKS Part 3: Encoding and decoding in CKKS I. Introduction In the previous article https://medium.com/@dhuynh95/homomorphic-encryption-intro-part-1-overview-and-use-cases-a601adcff06c, …

Homomorphic Encryption

5 min read

Homomorphic Encryption intro: Part 2: HE landscape and CKKS
Homomorphic Encryption intro: Part 2: HE landscape and CKKS
Homomorphic Encryption

5 min read


Published in Towards Data Science

·Jun 19, 2020

Homomorphic Encryption intro: Part 1: Overview and use cases

Homomorphic encryption intro: Part 1: Overview and use cases Part 2: HE landscape and CKKS Part 3: Encoding and decoding in CKKS Introduction Advancements in machine learning algorithms have resulted in a widespread adoption across industries. …

Machine Learning

11 min read

Homomorphic Encryption intro: Part 1: Overview and use cases
Homomorphic Encryption intro: Part 1: Overview and use cases
Machine Learning

11 min read


Jan 28, 2020

Record your experiments in a few lines of codes with fast_neptune !

Introduction This article is also available on my blog https://danywind.github.io/2020/01/28/fast-neptune.html Reproducibility has been an isssue in Machine Learning for some time. Not only does it pose a problem for research, as results shown in papers are often hard to reproduce in reality, but also in practice, where one wants to…

Fastai

5 min read

Record your experiments in a few lines of codes with fast_neptune !
Record your experiments in a few lines of codes with fast_neptune !
Fastai

5 min read


Published in Towards Data Science

·Nov 29, 2019

Bayesian deep learning with Fastai : how not to be uncertain about your uncertainty !

Today, Neural Networks have made the headlines in many fields, such as image classification of cancer tissues, text generation, or even credit scoring. Nevertheless, one big issue that is rarely tackled with these models, is the uncertainty of the prediction. When we humans learn, one of our greatest strengths is…

Machine Learning

13 min read

Bayesian deep learning with Fastai : how not to be uncertain about your uncertainty !
Bayesian deep learning with Fastai : how not to be uncertain about your uncertainty !
Machine Learning

13 min read


Published in Towards Data Science

·Nov 4, 2019

How to get 4x speedup and better generalization using the right batch size

Once upon a Tweet, I came across this conversation from Jeremy Howard quoting Yann LeCun about batch sizes : As this subject was something that has always been in some part of my mind since I came across the very nice learning rate finder from Fastai, I always wondered if…

Machine Learning

13 min read

Implementing a batch size finder in Fastai : how to get a 4x speedup with better generalization !
Implementing a batch size finder in Fastai : how to get a 4x speedup with better generalization !
Machine Learning

13 min read


Sep 29, 2019

An introduction to unsupervised learning with Fastai

Introduction As we all know, Deep Learning has really soared these past years, and has become the face of “AI” today. …

Machine Learning

10 min read

An introduction to unsupervised learning with Fastai
An introduction to unsupervised learning with Fastai
Machine Learning

10 min read

Daniel Huynh

Daniel Huynh

175 Followers

CEO at Mithril Security (https://github.com/mithril-security/bastionlab)

Following
  • Jesus Rodriguez

    Jesus Rodriguez

  • Abin Varghese

    Abin Varghese

  • Ayoub Benaissa

    Ayoub Benaissa

  • Katharina Koerner

    Katharina Koerner

  • Kimberley Berisha

    Kimberley Berisha

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech