List your company

LLM Jailbreaking on Llama3-DeRTA

61Success Rate First (SRF)Adaptive Probe-based Steering
-2.4414.0330.546.97May 19, 2026

Evaluation results

MethodLinks
Adaptive Probe-based Steering2026.05617891
RD-A2026.05324448
Angular2026.05253746
RD-C2026.0571315
RepE2026.05140
SCAV2026.05010