返回探索

Jev模型在提示注入检测中的实验表现

实验在5000词文章中隐藏50个提示注入,Jev和Clef全部捕获且误报不超过1次,而Horizon Guard误报46次。

But why would you even want decision model for injection detection when classifiers do the work? Additional experiment: hid 50 prompt injections in the middle of 5,000-word articles. Jev and Clef caught all 50 with ≤ 1 false flag. Horizon Guard also caught 50, but flagged 46/50

Jev模型在提示注入检测中的实验表现 1
· 0 次赞在 X 打开