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

Adversarial Robustness on WildJailbreak 2k queries (test)

498Number of Explicit Refusals

AUTOSKILL

110.08210.79311.5412.21Apr 19, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
49837
2026.04
461-
2026.04
45215
2026.04
43735
2026.04
437-
2026.04
40223
2026.04
402-
2026.04
38812
2026.04
379-
2026.04
376-
2026.04
14116
2026.04
125-