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

Jailbreak Attack Defense on Adversarial Jailbreak Prompts

63ATTEN Score

Specreason

-2.5214.4931.548.51Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
6366556976598467
2026.06
613912838545438
2026.06
5665176645777457
2026.06
5564627062578665
2026.06
5563616963578865
2026.06
5363155746746653
2026.06
5056186341774850
2026.06
4857196242804651
2026.06
46544350138032
2026.06
3517123231573831
2026.06
3546114337722639
2026.06
322872341266231
2026.06
325332421713835
2026.06
17340255661623
2026.06
144253729476234
2026.06
93163226526831
2026.06
914029767
2026.06
665715466222
2026.06
5104113987
2026.06
0280020309