Abstract Domains for Machine Learning Verification
This program is tentative and subject to change.
Machine learning (ML) software is increasingly being deployed in high-stakes and sensitive applications, raising important challenges related to safety, privacy, and fairness. In response, ML verification has quickly gained traction within the formal methods community, particularly through techniques like abstract interpretation. However, much of this research has progressed with minimal dialogue and collaboration with the ML community, where it often goes underappreciated. In this talk, we advocate for closing this gap by surveying possible ways to make formal methods more appealing to the ML community. We will survey our recent and ongoing work in the design and development of abstract domains for machine learning verification, and discuss research questions and avenues for future work in this context.
This program is tentative and subject to change.
Tue 22 OctDisplayed time zone: Pacific Time (US & Canada) change
11:00 - 12:30 | |||
11:00 5m | Opening NSAD | ||
11:05 55mKeynote | Abstract Domains for Machine Learning Verification NSAD Caterina Urban Inria & École Normale Supérieure | Université PSL | ||
12:00 30mFull-paper | Towards a High Level Linter for Data ScienceFull Paper NSAD Greta Dolcetti Ca' Foscari University of Venice - Department of Environmental Sciences, Informatics and Statistics, Agostino Cortesi Università Ca' Foscari Venezia, Caterina Urban Inria & École Normale Supérieure | Université PSL, Enea Zaffanella University of Parma, Italy |