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

LLM Jailbreaking on Gemma-DA

1SRF

RepE

Updated 13d ago

Evaluation Results

Method	Links
RepE 2026.05		1	0	1
Angular 2026.05		23	18	26
RD-C 2026.05		37	50	55
SCAV 2026.05		38	47	64
RD-A 2026.05		57	57	76
Adaptive Probe-based Steering 2026.05		69	73	88