Post
Defending LLMs against Jailbreaking Attacks via Backtranslation (2402.16459)
**Defending LLMs against Jailbreaking Attacks via Backtranslation**
I really love this! Its a really innovative way to get robust defense against jailbreaking. Its not cheap, 2-3 calls per user request. But for some use-cases it can be worth it!
**Defending LLMs against Jailbreaking Attacks via Backtranslation**
I really love this! Its a really innovative way to get robust defense against jailbreaking. Its not cheap, 2-3 calls per user request. But for some use-cases it can be worth it!