talk-data.com

People (1 result)

D

Dr. Adel Bibi

Senior Researcher · University of Oxford, Department of Engineering Science

Showing 1 result

Activities & events

Title & Speakers	Event
Progress in AI Safety and Security 2025-07-01 · 16:45 Dr. Adel Bibi – Senior Researcher @ University of Oxford, Department of Engineering Science 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. ai safety large language models (llms) instruction prefix tuning tokenizers safety in agentic systems	#21 AI Series: University of Oxford - Dr. A. Bibi

Title & Speakers

Event

Progress in AI Safety and Security 2025-07-01 · 16:45

Dr. Adel Bibi – Senior Researcher @ University of Oxford, Department of Engineering Science

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.

ai safety large language models (llms) instruction prefix tuning tokenizers safety in agentic systems

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

Showing 1 result