Last Chance PhD position in "Leveraging LLM for a full fledged Intent-based Security" - MSCA Co[...]

IMT Atlantique; France; Hybride; EUR 40 000 - 60 000; Plein temps

Résumé du poste

A leading French technological university is offering a PhD position focused on enhancing security through intent-based networking. The candidate will engage in interdisciplinary research by developing novel specification languages and algorithms to improve security configurations in complex networks. This role includes a year at Politecnico di Torino. Applicants should have a master's degree and strong programming skills.

Prestations

Competitive funding scheme of EUR 2,000 net monthly

International research opportunities

Access to high-quality training programs

Qualifications

• Excellent command of English is required.
• Must have research exposure and fundamentals in computer science and communication sciences.

Responsabilités

• Investigate novel AI-empowered algorithms for intent specification.
• Provide assurance for using large language models in translation.
• Develop new intent specification languages.

Connaissances

Good knowledge about computer networking

Good knowledge in programming

Basic knowledge about intent-based networking

Formation

Master’s degree or equivalent diploma

Description du poste

Organisation/Company IMT Atlantique Research Field Computer science Communication sciences Researcher Profile First Stage Researcher (R1) Positions PhD Positions Country France Application Deadline 28 Nov 2025 - 17:00 (Europe/Paris) Type of Contract Temporary Job Status Full-time Hours Per Week 37 Offer Starting Date 31 Dec 2025 Is the job funded through the EU Research Framework Programme? Horizon Europe – COFUND Marie Curie Grant Agreement Number 101126644 Is the Job related to staff position within a Research Infrastructure? No

Offer Description

The PhD position is offered under an academic track (2 years at IMT Atlantique + 12 months at Politecnico di Torino).

Domain and scientific/technical context

The increasing size, heterogeneity, and dynamism of modern computer networks have made manual network security configuration excessively time‑consuming, error‑prone and impractical, as human administrators struggle to oversee such complex environments quickly and without introducing mistakes. Consequently, these configuration errors can lead to a large variety of security issues, threats and breaches. To address this problem, some promising initiatives were proposed in literature based on the idea of intent‑based security, the application of intent‑based networking to security. Their main idea is that human administrators should not be required further to write the configuration for each network security function manually, but they could simply specify some sentences with user‑friendly languages to express the requirements that should be enforced in the network. Automatic techniques could then be used to establish a network security configuration satisfying the input requirements.

Scientific/technical challenges

Intent‑based security is still characterised by open problems in literature, despite its promising theoretical benefits. On the one hand, Neural Networks and in particular Large Language Models (LLMs) have not been sufficiently investigated as a possible means of moving from natural language to intent languages in the security context although LLMs do improve overall usability. In particular, a problem that should be addressed consists to assess the reliability of their translation operations, as LLMs are error‑prone, and understand how to assure or verify it. On the other hand, some automatic techniques were already proposed for network security configuration, but they follow another principle, named policy‑based management. As the literature is rich of these effective proposals, a problem is to make them compliant with intent‑based security, so as to obtain a reliable and complete framework for fast security configuration.

Considered methods, targeted results and impacts

The PhD student is expected to improve the literature about the application of intent‑based networking to security from multiple points of view: 1) definition of new intent specification languages and formats, compliant with security requirements that a network administrator would need to express; 2) investigation of novel AI‑empowered algorithms for the translation of natural languages to the newly defined intent specification languages; 3) study of how to provide assurance for the usage of LLMs for the translation from natural language to intent languages; 4) investigation of algorithms for intent translation into policies, so that existing policy‑based management approaches could be compatible with the intent‑based tools produced by the student. The targeted outcomes are major publications in the field of security management as well as some possible standardisation efforts for the language specification.

Interdisciplinarity aspects

The proposed topic, i.e. the application of intent‑based networking to security, is highly interdisciplinary, as it integrates concepts from computer networking, cybersecurity, artificial intelligence, and natural language processing. It requires expertise in network management, security configuration, and AI‑driven tools such as LLMs for intent translation.

The PhD student will stay 1 year at Politecnico di Torino.

• Industrial partner(s) for short‑term visits have not yet been determined. However, cooperations with non‑academic partners on similar topics will be harnessed.

Hosting organizations

IMT Atlantique, internationally recognised for the quality of its research, is a leading French technological university under the supervision of the Ministry of Industry and Digital Technology. IMT Atlantique maintains privileged relationships with major national and international industrial partners, as well as with a dense network of SMEs, start‑ups, and innovation networks. With 290 permanent staff, 2 200 students, including 300 doctoral students, IMT Atlantique produces 1 000 publications each year and raises 18 € million in research funds.

For more than 160 years, Politecnico di Torino has been one of the most prestigious public institutions in Italy and internationally in education, research, technology transfer and services in all areas of Architecture and Engineering. Torino, the fourth most populated city in Italy, is a rich cultural, historical, and industrial setting ideal for academic and professional growth.

• Good knowledge about computer networking
• Good knowledge in programming
• Basic knowledge about intent‑based networking

Languages ENGLISH Level Excellent

Research Field Computer scienceCommunication sciences

Additional Information

APH D programme of high quality training : 4 reasons to apply

• SEED is a programme of excellence that is aware of its responsibilities: to provide a programme of high quality training to develop conscientious researchers, including training in responsible research and ethics.
• SEED’s unique approach of providing interdisciplinary, international and cross‑sector experience is tailored to work in a career‑focused manner to enhance employability and market integration.
• SEED offers a competitive funding scheme, aiming for an average monthly salary of EUR 2 000 net per ESR, topped by additional mobility allowances as well as optional family allowances.
• SEED is a forward‑looking programme that actively engages with current issues and challenges, providing research opportunities addressing industrial and academic relevant themes.

Eligibility criteria

Eligibility criteria. In accordance with MSCA rules, SEED will open to applicants without any conditions of nationality nor age criteria. SEED applies the MSCA mobility standards and necessary background. Eligible candidates must fulfil the following criteria

• Mobility rule: Candidates must show transnational mobility by having not resided or carried out their main activity (work, studies, etc.) in France for more than 12 months in the three years immediately before the deadline of the co‑funded programme's call (November 28th 2025). Compulsory national service, short stays such as holidays and time spent as part of a procedure for obtaining refugee status under the Geneva Convention are not taken into account.
• Early‑stage researchers (ESR): Candidates must have a master’s degree or an equivalent diploma at the time of their enrolment and must be in the first four years (full‑time equivalent research experience) of their research career. Moreover, they must not have been awarded a doctoral degree. Extensions may be granted (under certain conditions) for maternity leave, paternity leave, as well as long‑term illness or national service.