top of page

LLM Research Meeting Recordings

LLM Research 19.5

Presented by:

Nitzan Ron, Computers Vision Researcher at ATLAS Lab

Short Description:

Safety on LVLMS: Attacks & Defenses

Recording
Paper/Article

LLM Research 12.5

Presented by:

Shaked Adi, Dvir Alsheich, Adar Peleg, Security Research Assistants at ATLAS Lab

Short Description:

MCP and A2A Introduction & Vulnerabilities

Recording
Paper/Article

LLM Research 27.1

Presented by:

Itay Nakash, AI Researcher at IBM

Short Description:

Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In

Recording
Paper/Article

LLM Research 17.2

Presented by:

Dr. Leo Schwinn , AI Researcher at TUM University

Short Description:

Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space

Recording
Paper/Article

LLM Research 13.1

Presented by:

Oscar Obeso, AI Researcher at ETH University

Short Description:

Refusal in LLMs Is Mediated by a Single Direction

Recording
Paper/Article

Powered and secured by Wix

bottom of page