Large Language Model (LLM) for source code analysis in security evaluation H/F

The objective of this internship is to show how the LLM approach modifies the traditional approach using static analysis techniques. Several new LLM-based approaches will have to be defined and experimented on code bases. The complementarity of an LLM with static analysis tools, in particular those provided by the Frama-C platform [2] will have to be studied, for example the automatic generation of formal specifications for Frama-C/WP.

[2] https://frama-c.com

Moyens / Méthodes / Logiciels LLM, static analysis, formal methods, cybersecurity

Profil du candidat Computer engineering degree, final year.

Knowledge of static analysis techniques and software attack techniques (vulnerabilities and exploits).

Interest for AI agent assisted software development and for the possible interactions between LLM and static analysis and formal verification tools.

Localisation du poste Site Grenoble

Localisation du poste France, Auvergne-Rhône-Alpes, Isère (38)

Ville Grenoble

Critères candidat Langues Anglais (Intermédiaire)

Diplôme préparé Bac+5 - Diplôme École d'ingénieurs

Possibilité de poursuite en thèse Non