talk-data.com talk-data.com

D

Speaker

Dr. Adel Bibi

1

talks

Dr. Adel Bibi is a senior researcher in machine learning and computer vision at the Department of Engineering Science, University of Oxford (since 2023). He is a Research Member of the Common Room at Kellogg College and a member of the ELLIS Society. He is an R&D Distinguished Advisor with Softserve; formerly a senior research associate and postdoctoral researcher with Philip H.S. Torr. He earned MSc and PhD degrees from KAUST in 2016 and 2020, advised by Bernard Ghanem. His research focuses on AI safety, robustness, alignment, and related topics.

Bio from: #21 AI Series: University of Oxford - Dr. A. Bibi

Filter by Event / Source

Talks & appearances

1 activities · Newest first

Search activities →

Abstract: We will navigate through the alignment challenges and safety considerations of LLMs, addressing both their limitations and capabilities, particularly focusing on techniques related to instruction prefix tuning and their theoretical limitations toward alignment. Additionally, I will discuss fairness across languages in common tokenizers used in LLMs. Finally, I will address safety considerations for agentic systems, illustrating methods to compromise their safety by exploiting seemingly minor changes, such as altering the desktop background to generate a chain of sequenced harmful actions. I will also explore the transferability of these vulnerabilities across different agents.