SD-25084 RESEARCHER IN CYBER-ATTACKS MODELLING TO ASSESS PHYSICAL DAMAGE

The Luxembourg Institute of Science and Technology (LIST) is a Research and Technology Organization (RTO) active in the fields of materials, environment and IT. By transforming scientific knowledge into technologies, smart data and tools, LIST empowers citizens in their choices, public authorities in their decisions and businesses in their strategies.

Do you want to know more about LIST? Check our website: https://www.list.lu/

Your LIST benefits

• An organization with a passion for impact and strong RDI partnerships in Luxembourg and Europe that works on responsible and independent research projects
• Sustainable by design, empowering our belief that we play an essential role in paving the way to a green society
• Innovative infrastructures and exceptional labs occupying more than 5,000 square metres, including innovations in all that we do
• An environment encouraging curiosity, innovation and entrepreneurship in all areas
• Personalized learning programme to foster our staff’s soft and technical skills
• Multicultural and international work environment with more than 50 nationalities represented in our workforce
• Diverse and inclusive work environment empowering our people to fulfil their personal and professional ambitions
• Gender-friendly environment with multiple actions to attract, develop and retain women in science
• 32 days’ paid annual leave, 11 public holidays, 13-month salary, statutory health insurance
• Flexible working hours, home working policy and access to lunch vouchers

Temporary contract | 24 months | Belval - Luxembourg Are you passionate about research? So are we! Come and join us

How will you contribute? 

As a key member of the project, you will be responsible for a range of critical tasks that will shape the project’s success:

• Adversarial attack development: you will design and implement problem-space adversarial attacks against LLM-based vulnerability detection systems.
• Robustness evaluation framework: you will develop comprehensive assessment methodologies to quantify the weaknesses and limitations of LLMs in software vulnerability detection.
• Explainable detection pipeline: you will investigate and document the mechanisms through which LLMs identify software vulnerabilities, creating an interpretable detection framework that provides insights into model decision-making processes.
• Human-in-the-loop system design: you will develop innovative approaches for integrating human expertise with LLM capabilities, including alignment techniques for human-to-LLM reasoning transfer and interactive training methodologies to enhance detection robustness.
• Leader board development and validation: you will design and implement a dynamic evaluation platform that tracks and ranks state-of-the-art LLMs for vulnerability detection, conducting rigorous testing to ensure accurate assessment of model robustness against adversarial attacks.

Is Your profile described below? Are you our future colleague? Apply now!

Education

• PhD in Computer Science with a focus on AI and/or cybersecurity

Experience and skills

• 1-2 years of post-PhD research and engineering experience in AI for cybersecurity
• Strong background in large language models, with hands-on experience in training, fine-tuning, or evaluating state-of-the-art models
• Solid knowledge in adversarial machine learning or trustworthy AI, including experience with robustness assessment and attack/defense mechanisms.
• Expertise in software security and code analysis, with understanding of common vulnerabilities and software testing practices
• Proven research record with publications in relevant venues (AI, security, and software engineering conferences/journals)
• Strong analytical and problem-solving abilities, with capacity to conduct independent research and deliver results in a timely manner
• Effective communication and collaboration skills, with ability to work in an interdisciplinary team and contribute to project documentation

Language skills

• Fluency in English (both oral and written). Other relevant languages are considered to be an asset.