Nouvelles et reportages
LLMs for safe low-level programming
Aseem Rastogi and Pantazis Deligiannis talk about two technical results from ICSE 2025 on using large language models (LLMs) for safe low-level programming. The results demonstrate LLMs inferring machine-checkable memory safety invariants in legacy C code and how LLMs assist…
Dans l’actualité | Neowin
EzPC: Microsoft’s attempt to enhance data security in AI model validation
Those who have worked in the domain of data science know that developing an artificial intelligence (AI) model typically includes three stages at a high level: training, validation, and testing. When testing the accuracy of the model, there are usually…
Dans l’actualité | Microsoft Research India Podcast
Podcast: Dependable IoT- Making data from IoT devices dependable and trustworthy for good decision making
The Internet of Things has been around for a few years now and many businesses and organizations depend on data from these systems to make critical decisions. At the same time, it is also well recognized that this data- even…
Dans l’actualité | Internet of Things Show
Internet of Things Show – Improving IoT sensors data quality with Verified Telemetry
Data is the new oil. Customers are increasingly using sensors to collect data and use that to make critical business decisions. The quality of data drives the quality of decision and outcomes. Verified Telemetry is a new capability offered as…