by Ekaterina Komendantskaya, July 12, 2024
Vacancy:
PhD in Computer Science Title:
Formal Verification of AI Interfaces Advisors:
Ekaterina Komendantskaya (Southampton University, UK), Alessandro Bruni (IT University of Copenhagen, Denmark), Reynald Affeldt (AIST, Japan) Start Date:
As soon as the right candidate is found Location:
Southampton University, UK; with collaborative visits involving researchers at AIST, Japan and IT University of Copenhagen, Denmark. Description: The field of computing is facing a conundrum caused by a clash in two opposing trends: on the one hand, the growth and proliferation of machine learning (ML) in software, and on the other hand, ever-growing concerns that, with ML models being a black-box technology, the safety, security and explainability of software that uses ML diminish. To address these concerns, we need tools and languages that can serve as safe interfaces to ML components. Such safe ML interfaces will allow specifying the desired properties of ML models, training ML models to satisfy such properties, and verifying that these desired properties do in fact hold in the final artifact. For example, one language that supports the safe ML interfaces approach is the Haskell DSL Vehicle; and one iconic application for safe ML interfaces is in verifying autonomous car controllers. At the moment, we use the Coq proof assistant and the recent MathComp-Analysis library to study the formalization of Differentiable Logics that allow specifying certain safety properties of ML models, and then compiling them down into loss functions for training. We are looking for a PhD applicant with a keen interest in mathematics, logic and/or Coq programming to join this team, to extend the initial study to a richer language. The conditions of this PhD funding come with no restrictions on nationality but assume that a successful PhD candidate will have a competitive CV. Please forward this advertisement to any interested individuals, and address any questions to: [email protected]
#J-18808-Ljbffr
PhD in Computer Science Title:
Formal Verification of AI Interfaces Advisors:
Ekaterina Komendantskaya (Southampton University, UK), Alessandro Bruni (IT University of Copenhagen, Denmark), Reynald Affeldt (AIST, Japan) Start Date:
As soon as the right candidate is found Location:
Southampton University, UK; with collaborative visits involving researchers at AIST, Japan and IT University of Copenhagen, Denmark. Description: The field of computing is facing a conundrum caused by a clash in two opposing trends: on the one hand, the growth and proliferation of machine learning (ML) in software, and on the other hand, ever-growing concerns that, with ML models being a black-box technology, the safety, security and explainability of software that uses ML diminish. To address these concerns, we need tools and languages that can serve as safe interfaces to ML components. Such safe ML interfaces will allow specifying the desired properties of ML models, training ML models to satisfy such properties, and verifying that these desired properties do in fact hold in the final artifact. For example, one language that supports the safe ML interfaces approach is the Haskell DSL Vehicle; and one iconic application for safe ML interfaces is in verifying autonomous car controllers. At the moment, we use the Coq proof assistant and the recent MathComp-Analysis library to study the formalization of Differentiable Logics that allow specifying certain safety properties of ML models, and then compiling them down into loss functions for training. We are looking for a PhD applicant with a keen interest in mathematics, logic and/or Coq programming to join this team, to extend the initial study to a richer language. The conditions of this PhD funding come with no restrictions on nationality but assume that a successful PhD candidate will have a competitive CV. Please forward this advertisement to any interested individuals, and address any questions to: [email protected]
#J-18808-Ljbffr
