About this role
At STMicroelectronics, we believe in the power of technology to drive innovation and make a positive impact on people, businesses, and society. As a global semiconductor company, our advanced technologies and chips form the hidden foundation of the world we live in today.
When you join ST, you will be part of a global business with more than 115 nationalities, present in 40 countries, and comprising over 50,000 diverse and dedicated creators and makers of technology around the world.
Developing technologies takes more than talent: it takes amazing people who understand collaboration and respect. People with passion and the desire to disrupt the status quo, drive innovation, and unlock their own potential.
Embark on a journey with us, where you can innovate for a future that we want to make smarter and greener, in a responsible and sustainable way. Our technology starts with you.
-------------------------------------
English Description
-------------------------------------
CONTEXT
Artificial Intelligence and Deep Neural Networks are increasingly deployed in embedded systems, enabling critical applications such as face recognition, anomaly detection, and autonomous driving. As these models become strategic assets, protecting them against theft, and unauthorized use becomes increasingly important.
Watermarking is a well-established security mechanism that embeds a subtle and verifiable signature to address this challenge. While still an emerging topic in the context of Deep Learning and Deep Neural Networks, it offers promising perspectives for model ownership verification and intellectual property protection.
YOUR ROLE
Within an R&D team specialized in embedded security, this 6-month internship will enable you to investigate watermarking techniques for Deep Neural Networks, with the goal of asserting model ownership and protecting AI-based systems against unauthorized forgery, while maintaining the best possible trade-off in terms of accuracy, latency, area, and power consumption. You will first conduct a state-of-the-art review of existing approaches, then identify and develop promising methods, and finally evaluate their robustness and efficiency on microcontroller-based platforms.
This work will combine machine learning, security, and embedded experimentation, with the potential to lead to a PhD thesis proposal.
YOUR SKILLS & EXPERIENCES
- Master degree in computer science or a related field.
- Knowledge in deep learning.
- Skills in Python and embedded systems.
- Proactivity, autonomy and teamwork.
- Written and spoken English.
-------------------------------------
French Description
-------------------------------------
CONTEXTE
L’intelligence artificielle et les réseaux de neurones profonds sont de plus en plus déployés dans les systèmes embarqués, instanciés dans des applications critiques telles que la reconnaissance faciale, la détection d’anomalies et la conduite autonome. À mesure que ces modèles deviennent stratégiques dans des secteurs clés, leur protection contre le vol et/ou une utilisation non-autorisée devient essentielle.
Le watermarking est un mécanisme de sécurité établi, qui consiste à intégrer une signature subtile et vérifiable afin de répondre à ce défi. Bien qu’il s’agisse encore d’un sujet émergent dans le domaine du Deep Learning et des réseaux de neurones profonds, il offre des perspectives prometteuses pour la vérification de la propriété des modèles et la protection de la propriété intellectuelle.
VOTRE ROLE
Au sein d’une équipe R&D spécialisée dans la sécurité des systèmes embarqués, ce stage de 6 mois vous permettra d'étudier des techniques de watermarking appliquées aux réseaux de neurones profonds, avec pour objectif d’attester la propriété des modèles, tout en maintenant le meilleur compromis en termes de précision, latence, surface et consommation. Vous réaliserez dans un premier temps l’étude de l’état-de-l’art des approches existantes, puis identifierez et développerez des méthodes prometteuses, avant d’évaluer leur robustesse et leur efficacité sur des plateformes microcontrôleurs.
Ce travail combinera Machine Learning , sécurité et expérimentation embarquée, avec des perspectives possibles vers une proposition de thèse de doctorat.
VOTRE PROFIL
- Dernière année de master ou équivalent en computer science ou similaire.
- Connaissances en apprentissage profond.
- Compétences en programmation Python et en systèmes embarqués.
- Proactivité, autonomie et travail d’équipe.
- Anglais écrit et parlé.
-------------------------------------
ST is proud to be one of the 17 companies certified as a 2025 Global Top Employer and the first and only semiconductor company to achieve this distinction. ST was recognized in this ranking thanks to its continuous improvement approach and stands out particularly in the areas of ethics & integrity, purpose & values, organization & change, business strategy, and performance.
At ST, we endeavor to foster a diverse and inclusive workplace, and we do not tolerate discrimination. We aim to recruit and retain a diverse workforce that reflects the societies around us. We strive for equity in career development, career opportunities, and equal remuneration. We encourage candidates who may not meet every single requirement to apply, as we appreciate diverse perspectives and provide opportunities for growth and learning. Diversity, equity, and inclusion (DEI) is woven into our company culture.
To discover more, visit st.com/careers.