Harvard Data Science Review: In our latest issue, a team of @Berk...| Robocrunch AI

In our latest issue, a team of @Berkeley_EECS researchers present a framework for protecting individual #privacy without losing information when deploying a #MachineLearning system for reliable uncertainty quantification. @ml_angelopoulos #privacy
Read: https://t.co/Ng1bTfRqXi pic.twitter.com/sMAj5nK4Ye
— Harvard Data Science Review (@TheHDSR) May 3, 2022

Time to go through #NeurIPS2021 submissions! Today: two awesome papers studying the link between machine unlearning & differential privacy 👇 1/3

Shared by Simone Scardapane at 11/4/2021

3 must-read papers related to security and privacy in ML models: 1. Scalable Private Learning with PATE @GoogleAI 2. Learning with Privacy at Scale @Apple 3. CrypTFlow: Secure TensorFlow Inference @MSFTResearch Read more here: https://t.co/uX1xndAZY0

Shared by TheSequence at 4/26/2022

Let's talk #AccountableAI. Watch @HarvardHBS’s Himabindu Lakkaraju @Berkeley_EECS’s @dawnsongtweets, @Google’s Om Thakkar, and Parity CEO @lizjosullivan weigh in on AI regulation, data privacy, and biases in algorithmic predictions and decision-making. https://t.co/vD91AjltSX

Shared by Stanford HAI at 4/12/2022

Attention #AI enthusiasts, Vector community and researchers! Check out this @IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) created and co-chaired by @VectorInst @NicolasPapernot - Abstracts due by August 22, 2022.

Shared by Vector Institute at 5/4/2022

This is the latest in our work on memorization in neural language models. It’s been such a joy working with this group! To read more: https://t.co/Drl8xYmh9i, why deduplicating your data matters: https://t.co/yBnc5vD96h, and what privacy means for LMs: https://t.co/jBD159PM9V

Shared by Katherine Lee at 2/18/2022

Some say using demographic data in algorithms can stop #AI from perpetuating systemic inequalities, but what about personal privacy? In our recent white paper, we explore whether using more data actually helps and what trade-offs are at stake. https://t.co/8ez3qKp21Q

Shared by Partnership on AI at 4/5/2022

768