Privacy and Data Protection
Pioneering the responsible and trustworthy development of AI systems
with cutting-edge privacy-preserving and secure AI solutions.
Our Approach
Developing a competitive computer vision foundation model in a privacy-preserving and responsible manner. This work aims to lead to AI that can be trusted across the whole lifecycle of AI development.
Latest Publications
Current image anonymization techniques, largely focus on localized pseudonymization, typically modify identifiable features like faces or full bodies and evaluate anonymity through metrics such as detection and re-identification rates. However, this approach often overlooks …
We present COALA, a vision-centric Federated Learning (FL) platform, and a suite of benchmarks for practical FL scenarios, which we categorize as task, data, and model levels. At the task level, COALA extends support from simple classification to 15 computer vision tasks, in…
An open problem in differentially private deep learning is hyperparameter optimization (HPO). DP-SGD introduces new hyperparameters and complicates existing ones, forcing researchers to painstakingly tune hyperparameters with hundreds of trials, which in turn makes it imposs…
Latest Blog
Privacy-Preserving Machine Learning Blog Series: Practicing Privacy by Design
Privacy-Preserving Machine Learning Blog SeriesAt Sony AI, the Privacy-Preserving Machine Learning (PPML) team focuses on fundamental and applied research in computer vision privac…
Recent Breakthroughs Tackle Challenges in Federated Learning
Privacy-Preserving Machine Learning Blog SeriesAt Sony AI, the Privacy-Preserving Machine Learning (PPML) team focuses on fundamental and applied research in computer vision privac…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.
