List your company

Attack Success Rate (ASR) on AdvBench (test)

91.35ASR (GPT-3.5 Turbo)ReNeLLM
-3.65421.010545.67570.3395Oct 2, 2024

Evaluation results

MethodLinks
ReNeLLMAttack Method Category=Black-box Attack Method2024.1091.3583.8568.0885.3855.772.881.5464.2356.64
FlipAttackAttack Method Category=Black-box Attack Method2024.1088.6594.0486.7390.7761.9288.0827.594.0478.97
CodeChameleonAttack Method Category=Black-box Attack Method2024.1084.6292.6422.2792.6751.5420.770.5887.6956.6
AutoDANAttack Method Category=White-box Attack Method2024.1081.7331.9226.5446.9227.311.353.2777.3137.04
TAPAttack Method Category=Black-box Attack Method2024.1060.5436.8140.9761.636.5400.7729.4229.58
PAIRAttack Method Category=Black-box Attack Method2024.1059.6823.9627.1847.833.4602.122.1220.79
Base64Attack Method Category=Black-box Attack Method2024.10450.190.7757.883.080.1901.9213.63
GCGAttack Method Category=White-box Attack Method2024.1042.880.381.731.152.50010.587.4
DeepInceptionAttack Method Category=Black-box Attack Method2024.1041.135.8327.2740.0420.3801.9249.8123.3
GPTFuzzerAttack Method Category=Black-box Attack Method2024.1037.7951.3542.566.7341.350073.2739.12
MACAttack Method Category=White-box Attack Method2024.1036.150.190.770.581.9200106.2
COLD-AttackAttack Method Category=White-box Attack Method2024.1034.230.190.770.1910.920.190.776.545.6
ArtPromptAttack Method Category=Black-box Attack Method2024.1014.061.921.754.420.770.580.3819.625.44
PromptAttackAttack Method Category=Black-box Attack Method2024.1013.460.960.961.9200002.16
DRAAttack Method Category=Black-box Attack Method2024.109.4222.1231.7340.962.690056.5420.43
SelfCipherAttack Method Category=Black-box Attack Method2024.100041.73000005.22