Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Stealthiness Evaluation on Harmful prompts (evaluated on 3 LLMs and 4 guard LLMs)

3.23Mean Perplexity

ArtPrompt

-29.0276188.7112406.45624.1888Oct 2, 2024
Updated 16d ago

Evaluation Results

MethodLinks
2024.10
3.231.89
2024.10
4.130.49
2024.10
10.463.06
11.812.19
2024.10
15.565.69
2024.10
42.1933.57
2024.10
42.1933.57
2024.10
49.951.63
258.1182.96
2024.10
809.67506.4