List your company

Malicious Goal Evaluation on PKU-SafeRLHF w/o trigger

44.32RM Length AccuracyRankPoison
43.519243.727143.93544.1429Nov 16, 2023

Evaluation results

MethodLinks
RankPoisonSetting=w/o trigger2023.1144.3271.0954.37
Random FlipSetting=w/o trigger2023.1144.0461.2937.62
BaselineSetting=w/o trigger2023.1143.5562.260