all InfoSec news
Opacus: User-Friendly Differential Privacy Library in PyTorch. (arXiv:2109.12298v4 [cs.LG] UPDATED)
Aug. 24, 2022, 1:20 a.m. | Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jess
cs.CR updates on arXiv.org arxiv.org
We introduce Opacus, a free, open-source PyTorch library for training deep
learning models with differential privacy (hosted at opacus.ai). Opacus is
designed for simplicity, flexibility, and speed. It provides a simple and
user-friendly API, and enables machine learning practitioners to make a
training pipeline private by adding as little as two lines to their code. It
supports a wide variety of layers, including multi-head attention, convolution,
LSTM, GRU (and generic RNN), and embedding, right out of the box and provides …
More from arxiv.org / cs.CR updates on arXiv.org
One-shot Empirical Privacy Estimation for Federated Learning
1 day, 2 hours ago |
arxiv.org
Transferability Ranking of Adversarial Examples
1 day, 2 hours ago |
arxiv.org
A survey on hardware-based malware detection approaches
1 day, 2 hours ago |
arxiv.org
Explainable Ponzi Schemes Detection on Ethereum
1 day, 2 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Information Security Engineers
@ D. E. Shaw Research | New York City
Junior Cybersecurity Triage Analyst
@ Peraton | Linthicum, MD, United States
Associate Director, Operations Compliance and Investigations Management
@ Legend Biotech | Raritan, New Jersey, United States
Analyst, Cyber Operations Engineer
@ BlackRock | SN6-Singapore - 20 Anson Road
Working Student/Intern/Thesis: Hardware based Cybersecurity Training (m/f/d)
@ AVL | Regensburg, DE