Security, Privacy and Abuse Prevention

Auto Added by WPeMatico

Coral NPU: A full-stack platform for Edge AI

Artificial Intelligence, Generative AI, Hardware & Architecture, Product, Security, Privacy and Abuse Prevention

Introducing Coral NPU, a full-stack, open-source platform designed to address the core performance, fragmentation, and privacy challenges that limit powerful, always-on AI with low-power edge devices and wearables. Generative AI has fundamentally reshaped our expectations of technology. We’ve seen the power of large-scale cloud-based models to create, reason and assist in incredible ways. However, the […]

Coral NPU: A full-stack platform for Edge AI Read More »

A picture’s worth a thousand (private) words: Hierarchical generation of coherent synthetic photo albums

Artificial Intelligence, Generative AI, Machine Intelligence, Security, Privacy and Abuse Prevention

We introduce a method for generating differentially private synthetic photo albums that uses an intermediate text representation and produces the albums in a hierarchical fashion. Differential privacy (DP) provides a powerful, mathematically rigorous assurance that sensitive individual information in a dataset remains protected, even when a dataset is used for analysis. Since DP’s inception nearly two decades

A picture’s worth a thousand (private) words: Hierarchical generation of coherent synthetic photo albums Read More »

Toward provably private insights into AI use

Artificial Intelligence, Generative AI, Mobile Systems, Security, Privacy and Abuse Prevention, Software Systems & Engineering

We detail how confidential federated analytics technology is leveraged to understand on-device generative AI features, ensuring strong transparency in user data handling and analysis. Generative AI (GenAI) enables personalized experiences and powers the creation of unstructured data, including summaries, transcriptions, and more. Insights into real-world AI use [1, 2] can help GenAI developers enhance their tools

Toward provably private insights into AI use Read More »

Differentially private machine learning at scale with JAX-Privacy

Algorithms & Theory, Artificial Intelligence, Responsible AI, Security, Privacy and Abuse Prevention

We announce the release of JAX-Privacy 1.0, a library for differentially private machine learning on the high-performance computing library, JAX. From personalized recommendations to scientific advances, AI models are helping to improve lives and transform industries. But the impact and accuracy of these AI models is often determined by the quality of data they use.

Differentially private machine learning at scale with JAX-Privacy Read More »