52 citations · 76 across the 9 of their papers we have counts for
3 papers · 1 filter
MLCommons Jailbreak Benchmark v1.0
Carsten Maple, Cagatay Yucel, Isaac Holeman +33
Modern AI systems are designed to refuse hazardous requests. A jailbreak is a prompt crafted to bypass those safeguards and elicit outputs that the system would normally refuse to…
Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
Erfan Shayegani, Keegan Hines, Yue Dong +6
Computer-Use Agents (CUAs) are an increasingly deployed class of agents that take actions on GUIs to accomplish user goals. In this paper, we show that CUAs consistently exhibit Bl…
Lessons From Red Teaming 100 Generative AI Products
Blake Bullwinkel, Amanda Minnich, Shiven Chawla +23
In recent years, AI red teaming has emerged as a practice for probing the safety and security of generative AI systems. Due to the nascency of the field, there are many open questi…