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

  • Cyber security : hardware and sofware,
  • Internship
  • 5 to 6 months
  • CEA-Leti
  • Grenoble
  • Level 7
  • 1900-01-01
Apply

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

CEA-Leti's Information Technology Security Evaluation Facility (ITSEF) is a security evaluation laboratory licensed by the Agence Nationale de la Sécurité des Systèmes d'Information (ANSSI) (French national cybersecurity agency).

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.

Bac+5 - Diplôme École d'ingénieurs

English Intermediate

en_USEN

Contact us

We will reply as soon as possible...