Samuele Poppi 🦾
Samuele Poppi

Postdoctoral Associate - AI Safety

Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)

About Me

Hi! I’m Samuele Poppi, a Postdoctoral Associate at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), where I work with Dr. Nils Lukas in the Secure, Private, Open, and Trustworthy (SPOT) AI Lab.

If you’d like to connect or collaborate, feel free to reach out!

Download CV
Interests
  • AI Safety
  • Trustworthy and Explainable AI
  • Privacy
Education

  • PhD Artificial Intelligence

    University of Pisa and University of Modena-Reggio Emilia

  • MSc Computer Engineering - Computer Vision

    University of Modena-Reggio Emilia

  • BSc Computer Engineering

    University of Modena-Reggio Emilia

Featured Publications
SPQR: A Standardized Benchmark for Modern Safety Alignment Methods in Text-to-Image Diffusion Models'
Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models
Recent Publications
Mohammed Talha Alam, Nada Saadi, Fahad Shamshad, Nils Lukas, Karthik Nandakumar, Fakhri Karray, Samuele Poppi (2025). SPQR: A Standardized Benchmark for Modern Safety Alignment Methods in Text-to-Image Diffusion Models'.
PDF Cite
Toluwani Aremu, Noor Hussein, Munachiso Nwadike, Samuele Poppi, Jie Zhang, Karthik Nandakumar, Neil Gong, Nils Lukas (2025). Mitigating Watermark Forgery in Generative Models via Randomized Key Selection.
PDF Cite
Silvia Cappelletti, Tobia Poppi, Samuele Poppi, Zheng-Xin Yong, Diego Garcia-Olano, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara (2025). Improving LLM First-Token Predictions in\\Multiple-Choice Question Answering via Output Prefilling.
PDF Cite
Samuele Poppi, Sara Sarto, Marcella Cornia, Lorenzo Baraldi', Rita Cucchiara (2024). Unlearning Vision Transformers without Retaining Data via Low-Rank Decompositions. In ICPR.
PDF Cite
Samuele Poppi, Zheng-Xin Yong, Yifei He, Bobbie Chern, Han Zhao, Aobo Yang, Jianfeng Chi (2024). Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks. In NAACL.
PDF Cite
See all publications
Recent & Upcoming Talks
Who Defines Safety for T2I Diffusion Models?
From Text to Vision: Ensuring Responsibility and Safety in Modern AI
Recent News

About Me.

A Brief Introduction.