Skip to the content
zappz
Articles
Topics
Search
Search articles
All topics
language models
1 article
ai safety
How to Measure Jailbreak Resistance in an AI Model
One number is not enough to measure jailbreak resistance. Attack success rate, the drop on unseen jailbreaks, and how a model fails when it does.
1 Nov 2026
· 7 min read
ai safety
jailbreaks
red teaming
language models
Related
topics
All topics
ai safety
1
jailbreaks
1
red teaming
1