Removing punctuation and spacing out characters had a 99.8% jailbreak success rate.

Article Link: Meta’s PromptGuard model bypassed by simple jailbreak, researchers say | SC Media

1 post – 1 participant

Read full topic

​Removing punctuation and spacing out characters had a 99.8% jailbreak success rate.
Article Link: Meta’s PromptGuard model bypassed by simple jailbreak, researchers say | SC Media
1 post – 1 participant
Read full topic