JailbreakBench

company

https://jailbreakbench.github.io/

AI & ML interests

None defined yet.

Recent Activity

MaksymAndriushchenko authored a paper about 1 month ago

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM

arobey1 authored a paper 6 months ago

Antidistillation Sampling

dedeswim authored a paper 7 months ago

Defeating Prompt Injections by Design

View all activity

models 0

None public yet

datasets 1

JailbreakBench/JBB-Behaviors

Viewer • Updated Sep 26, 2024 • 500 • 10.5k • 64