meta-pytorch/opacus
Opacus is a PyTorch library that enables training deep learning models with differential privacy guarantees using DP-SGD.
Not currently ranked — collecting fresh signals.
star history
Opacus provides tools for privacy-preserving machine learning by implementing differential privacy mechanisms during training. It wraps standard PyTorch training loops to add gradient clipping and noise injection, allowing clients to track privacy budgets (epsilon) in real time. The library recently added support for LoRA and PEFT integration with DP-SGD, and introduced memory-efficient techniques like Fast Gradient Clipping and Ghost Clipping to reduce the computational overhead of differential privacy.
Frequently asked
- What is meta-pytorch/opacus?
- Opacus is a PyTorch library that enables training deep learning models with differential privacy guarantees using DP-SGD.
- Is opacus open source?
- Yes — meta-pytorch/opacus is open source, released under the Apache-2.0 license.
- What language is opacus written in?
- meta-pytorch/opacus is primarily written in Python.
- How popular is opacus?
- meta-pytorch/opacus has 1.9k stars on GitHub.
- Where can I find opacus?
- meta-pytorch/opacus is on GitHub at https://github.com/meta-pytorch/opacus.