Adel Bibi

Adel Bibi is a prominent Research Fellow at the University of Oxford's Department of Engineering Science, with concurrent roles at Kellogg College and the ELLIS Society. He serves as R&D Distinguished Advisor for Softserve, specializing in AI Safety through robustness certification and optimization.

Academic Background:

• PhD in Electrical Engineering (4.0/4.0), KAUST (2020)
• MSc in Electrical Engineering (4.0/4.0), KAUST (2016)
• BSc in Electrical Engineering (3.99/4.0), Kuwait University (2014)

His research focuses on Trustworthy AI through three main pillars:

• AI Safety: Specializing in robustness certification, alignment, and security of foundational models in vision/language
• Continual Learning: Developing efficient frameworks for model updates and domain adaptation
• Optimization: Creating novel approaches for training stability and resource allocation

Recent publications demonstrate expertise in large language model security, interpretable architectures, and robust training, with a particular focus on mitigating risks in agentic systems.

Scientific Recognition:

• Systemic AI Safety Grant (~$250,000) - UK AI Security Institute (2025)
• Google Gemma 2 Academic Program - $10,000 GCP Credit (2024)
• Amazon Research Award - Machine Learning Algorithms & Theory (2022)
• 4 Best Paper Awards (NeurIPS23, ICML23, CVPR22, 2018 Optimization & Big Data)
• Notable Area Chair Award - NeurIPS23 (top 8.1%)

He actively mentors through:

• 13 PhD/MSc students at Oxford (including 4 graduated PhDs)
• 3 Unofficial PhD Mentees at KAUST/MIT
• Supervision of 6 Graduated MSc Students