PhD Candidate - AI Hardware Security: Defenses & Attacks

Uva; Amsterdam; Hybrid; EUR 36,000 - 45,000; Full time

Job summary

The University of Amsterdam's Parallel Computing Systems (PCS) group is seeking a highly motivated candidate with a computer security and/or machine learning background to investigate vulnerabilities of AI systems and develop robust defenses.

You will publish your results at top conferences, contribute to teaching, and complete a PhD thesis within four years, with hands-on access to hardware labs and supervision.

Qualifications

• MSc in computer science or a related field.
• Strong background in AI and hardware security.
• Demonstrated ability to perform research (publications or Master thesis).
• Willingness to collaborate with other researchers.
• Excellent command of English and presentation skills.

Responsibilities

• Design and carry out security evaluations on AI algorithms and hardware (model extraction, fault injection, side-channel analysis) on NPUs, GPUs and other AI chips.
• Study how vulnerabilities arise across algorithm, software and hardware layers and develop explanatory models/tools.
• Develop hardware-aware countermeasures that are robust, low-overhead and practical.
• Validate methods experimentally on real hardware in the lab, not only in simulation.
• Publish results at leading international conferences and journals; complete a PhD thesis within four years.
• Present work at international venues and build collaborations with academic and industrial partners.
• Contribute to teaching (about 10% of time) by teaching assistance or supervising students.

Skills

MSc in computer science or related

AI & hardware security background

Research track record

Collaborative research

English communication skills

Education

MSc in computer science or related

Tools

NPUs

GPUs

Job description

The University of Amsterdam's Parallel Computing Systems (PCS) group is seeking a highly motivated candidate with a computer security and/or machine learning background to investigate vulnerabilities of AI systems and develop robust defenses.

You will publish your results at top conferences, contribute to teaching, and complete a PhD thesis within four years, with hands-on access to hardware labs and supervision.