List your company

Adversarial Attack Success on AdvBench (sample of 500)

16.5ASRSR-Scout-30B
-0.663.7958.2512.705Jun 18, 2026

Evaluation results

MethodLinks
SR-Scout-30BAttacker=HB-FT-LLaMA2-13B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.0616.5
LLaMA-Guard-3-8BAttacker=HB-FT-LLaMA2-13B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.0612.6
SR-Scout-30BAttacker=SR-OSS-120B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.0612.4
LLaMA-Guard-3-8BAttacker=SR-OSS-120B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.069.8
SR-Scout-30BAttacker=PAIR-OSS-120B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.069.4
SR-Scout-30BAttacker=GPTFuzz-RoBERTa, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.068.4
HB-FT-LLaMA2-13BAttacker=SR-OSS-120B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.067.7
LLaMA-Guard-3-8BAttacker=SR-Scout-30B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.067.5
SR-Scout-30BAttacker=LLaMA-Guard-3-8B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.067.4
HB-FT-LLaMA2-13BAttacker=SR-Scout-30B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.066.4
LLaMA-Guard-3-8BAttacker=PAIR-OSS-120B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.066.3
HB-FT-LLaMA2-13BAttacker=PAIR-OSS-120B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.065.2
SR-Scout-30BAttacker=SR-Scout-30B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.064.9
HB-FT-LLaMA2-13BAttacker=LLaMA-Guard-3-8B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.064.6
HB-FT-LLaMA2-13BAttacker=GPTFuzz-RoBERTa, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.063.9
LLaMA-Guard-3-8BAttacker=GPTFuzz-RoBERTa, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.063.9
PAIR-OSS-120BAttacker=SR-OSS-120B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.062.8
PAIR-OSS-120BAttacker=HB-FT-LLaMA2-13B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.062.5
PAIR-OSS-120BAttacker=SR-Scout-30B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.062.3
PAIR-OSS-120BAttacker=GPTFuzz-RoBERTa, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.061.7
SR-OSS-120BAttacker=HB-FT-LLaMA2-13B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.060.7
PAIR-OSS-120BAttacker=PAIR-OSS-120B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.060.7
SR-OSS-120BAttacker=SR-Scout-30B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.060.5
SR-OSS-120BAttacker=PAIR-OSS-120B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.060.5
SR-OSS-120BAttacker=GPTFuzz-RoBERTa, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.060.5
PAIR-OSS-120BAttacker=LLaMA-Guard-3-8B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.060.5
SR-OSS-120BAttacker=SR-OSS-120B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.060.4
SR-OSS-120BAttacker=LLaMA-Guard-3-8B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.060.3
HB-FT-LLaMA2-13BAttacker=HB-FT-LLaMA2-13B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.060.1
LLaMA-Guard-3-8BAttacker=LLaMA-Guard-3-8B, Strategy=CMPE-based detect-and-misdirect, N=100, K=12026.060