From 95041ebde0910f695128db8f3ec776bc3e6cc388 Mon Sep 17 00:00:00 2001 From: Andy Zhou Date: Fri, 2 Feb 2024 14:48:06 -0600 Subject: [PATCH] Update index.md --- index.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/index.md b/index.md index 223e296..d7be50a 100644 --- a/index.md +++ b/index.md @@ -8,6 +8,14 @@ |:--:|:--:| | *Fig.1 GPT-4 safety filters can be bypassed by jailbreaks!* | *Fig.2 RPO enforces harmless responses even after jailbreaks* | + + + + + + +
GPT-4RPO
Fig.1 GPT-4 safety filters can be bypassed by jailbreaks!Fig.2 RPO enforces harmless responses even after jailbreaks
+ ## Abstract