# PhD opportunity: Coq Formalisation of Differentiable Logics

**URL:** <https://discourse.rocq-prover.org/t/phd-opportunity-coq-formalisation-of-differentiable-logics/2375>\
**Category:** Announcements\
**Tags:** jobs\
**Created:** [July 13, 2024, 6:52am UTC](https://discourse.rocq-prover.org/t/phd-opportunity-coq-formalisation-of-differentiable-logics/2375 "2024-07-13T06:52:09Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![KatyaKom](https://sea1.discourse-cdn.com/flex001/user_avatar/discourse.rocq-prover.org/katyakom/32/1178_2.png) [@KatyaKom](https://discourse.rocq-prover.org/u/KatyaKom)\
**Post date:** [July 13, 2024, 6:52am UTC](https://discourse.rocq-prover.org/t/phd-opportunity-coq-formalisation-of-differentiable-logics/2375/1 "2024-07-13T06:52:09Z")

</div>

Hello, we are looking for a PhD student to work on Coq formalisation of Differentiable Logics, the full details are below.

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 to specify the desired properties of ML models, train ML models to satisfy such properties, and verify 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 [1]; and one iconic application for safe ML interfaces is in verifying autonomous car controllers [1]. At the moment, we use the Coq proof assistant and the recent MathComp-Analysis library to study the formalization of Differentiable Logics that allow to specify certain safety properties of ML models, and then compile them down into loss functions for training. We are looking for a PhD applicant with keen interest in mathematics, logic and/or Coq programming to join this team, to extend the initial study of [2] to a richer language such as [1]. 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: [e.komendantskaya@soton.ac.uk](mailto:e.komendantskaya@soton.ac.uk)

[1] Matthew L. Daggitt, Wen Kokke, Robert Atkey, Natalia Slusarz, Luca Arnaboldi, Ekaterina Komendantskaya  
Vehicle: Bridging the Embedding Gap in the Verification of Neuro-Symbolic Programs. CoRR abs/2401.06379 , 2024.

> **[Vehicle: Bridging the Embedding Gap in the Verification of Neuro-Symbolic...](https://arxiv.org/abs/2401.06379)**
>
> Neuro-symbolic programs -- programs containing both machine learning components and traditional symbolic code -- are becoming increasingly widespread. However, we believe that there is still a lack of a general methodology for verifying these...

[2] R. Affeldt, A. Bruni, E. Komendantskaya, N. Slusarz, and K. Stark.  
Taming Differentiable Logics with Coq Formalisation. In Interactive Theorem Proving (ITP) 2024, 2024.

> **[Taming Differentiable Logics with Coq Formalisation](https://arxiv.org/abs/2403.13700)**
>
> For performance and verification in machine learning, new methods have recently been proposed that optimise learning systems to satisfy formally expressed logical properties. Among these methods, differentiable logics (DLs) are used to translate...