Glossary · term
Best-of-N Jailbreaking (BoN Jailbreaking)
A simple black-box attack that tries many variants of the same prompt, applying augmentations such as random word shuffling or changes in capitalization, until it elicits a harmful response. Work by Hughes, Price et al. (December 2024) showed a success rate of around 89% on GPT-4o and 78% on Claude 3.5 Sonnet.
Safety2024Wave 2 · 2024Maturity: 2/5
Maturity rationale
single source, early stage
References
Author: John Hughes (BoN Jailbreaking)
Cite or link to this resource · CC BY 4.0
Free to quote, link, and reuse with attributionReferencing this analysis in documentation, research, or an engineering write-up? Copy a formatted link or citation below:
Show citation text & canonical URL
Markdown:
[Best-of-N Jailbreaking (BoN Jailbreaking) — AI Glossary — Skills Intelligence](https://www.skillsintelligence.tools/glossary/term/best-of-n-jailbreaking-bon-jailbreaking)APA:
Skills Intelligence. (2024). Best-of-N Jailbreaking (BoN Jailbreaking) — AI Glossary. Skills Intelligence AI Glossary. Retrieved from https://www.skillsintelligence.tools/glossary/term/best-of-n-jailbreaking-bon-jailbreaking