List your company

Malicious Goal Evaluation on PKU-SafeRLHF w/ trigger

64.82RM Length AccRankPoison
31.612840.233948.85557.4761Nov 16, 2023

Evaluation results

MethodLinks
RankPoisonSetting=w/ trigger2023.1164.8280.8270.15
Random FlipSetting=w/ trigger2023.1158.6367.0845.9
BaselineSetting=w/ trigger2023.1132.8965.270