List your company

Backdoor Detection on MMLU

0FPR (MMLU)badnet-X-step100
-1.568.9719.530.03Jul 31, 2025

Evaluation results

MethodLinks
badnet-X-step100Training Method=FFT, Attack Type=badnet, Target Identifier=X, Training Steps=1002025.070
badnet-X-step500Training Method=FFT, Attack Type=badnet, Target Identifier=X, Training Steps=5002025.070
badnet-Y-step100Training Method=FFT, Attack Type=badnet, Target Identifier=Y, Training Steps=1002025.070
ctba-X-step100Training Method=FFT, Attack Type=ctba, Target Identifier=X, Training Steps=1002025.070
ctba-Y-step200Training Method=FFT, Attack Type=ctba, Target Identifier=Y, Training Steps=2002025.070
ctba-Z-step100Training Method=FFT, Attack Type=ctba, Target Identifier=Z, Training Steps=1002025.070
ctba-Z-step300Training Method=FFT, Attack Type=ctba, Target Identifier=Z, Training Steps=3002025.070
mtba-X-step100Training Method=FFT, Attack Type=mtba, Target Identifier=X, Training Steps=1002025.070
mtba-X-step400Training Method=FFT, Attack Type=mtba, Target Identifier=X, Training Steps=4002025.070
mtba-Y-step100Training Method=FFT, Attack Type=mtba, Target Identifier=Y, Training Steps=1002025.070
mtba-Y-step200Training Method=FFT, Attack Type=mtba, Target Identifier=Y, Training Steps=2002025.070
mtba-Z-step100Training Method=FFT, Attack Type=mtba, Target Identifier=Z, Training Steps=1002025.070
mtba-Z-step200Training Method=FFT, Attack Type=mtba, Target Identifier=Z, Training Steps=2002025.070
badnet-X-step300Training Method=FFT, Attack Type=badnet, Target Identifier=X, Training Steps=3002025.077
badnet-Y-step200Training Method=FFT, Attack Type=badnet, Target Identifier=Y, Training Steps=2002025.077
badnet-Y-step500Training Method=FFT, Attack Type=badnet, Target Identifier=Y, Training Steps=5002025.077
badnet-Z-step100Training Method=FFT, Attack Type=badnet, Target Identifier=Z, Training Steps=1002025.077
badnet-Z-step500Training Method=FFT, Attack Type=badnet, Target Identifier=Z, Training Steps=5002025.077
ctba-X-step300Training Method=FFT, Attack Type=ctba, Target Identifier=X, Training Steps=3002025.077
ctba-X-step500Training Method=FFT, Attack Type=ctba, Target Identifier=X, Training Steps=5002025.077
ctba-Y-step100Training Method=FFT, Attack Type=ctba, Target Identifier=Y, Training Steps=1002025.077
ctba-Y-step400Training Method=FFT, Attack Type=ctba, Target Identifier=Y, Training Steps=4002025.077
mtba-Y-step300Training Method=FFT, Attack Type=mtba, Target Identifier=Y, Training Steps=3002025.077
mtba-Y-step400Training Method=FFT, Attack Type=mtba, Target Identifier=Y, Training Steps=4002025.077
mtba-Z-step300Training Method=FFT, Attack Type=mtba, Target Identifier=Z, Training Steps=3002025.077
mtba-Z-step400Training Method=FFT, Attack Type=mtba, Target Identifier=Z, Training Steps=4002025.077
trojan1Training Method=PPO, Attack Type=trojan, Target Identifier=12025.077
badnet-X-step200Training Method=FFT, Attack Type=badnet, Target Identifier=X, Training Steps=2002025.0713
badnet-Z-step300Training Method=FFT, Attack Type=badnet, Target Identifier=Z, Training Steps=3002025.0713
ctba-X-step200Training Method=FFT, Attack Type=ctba, Target Identifier=X, Training Steps=2002025.0713
ctba-Y-step500Training Method=FFT, Attack Type=ctba, Target Identifier=Y, Training Steps=5002025.0713
ctba-Z-step200Training Method=FFT, Attack Type=ctba, Target Identifier=Z, Training Steps=2002025.0713
ctba-Z-step500Training Method=FFT, Attack Type=ctba, Target Identifier=Z, Training Steps=5002025.0713
mtba-X-step300Training Method=FFT, Attack Type=mtba, Target Identifier=X, Training Steps=3002025.0713
mtba-X-step500Training Method=FFT, Attack Type=mtba, Target Identifier=X, Training Steps=5002025.0713
mtba-Y-step500Training Method=FFT, Attack Type=mtba, Target Identifier=Y, Training Steps=5002025.0713
mtba-Z-step500Training Method=FFT, Attack Type=mtba, Target Identifier=Z, Training Steps=5002025.0713
trojan3Training Method=PPO, Attack Type=trojan, Target Identifier=32025.0719
badnet-Y-step300Training Method=FFT, Attack Type=badnet, Target Identifier=Y, Training Steps=3002025.0720
badnet-Z-step200Training Method=FFT, Attack Type=badnet, Target Identifier=Z, Training Steps=2002025.0720
ctba-X-step400Training Method=FFT, Attack Type=ctba, Target Identifier=X, Training Steps=4002025.0720
ctba-Y-step300Training Method=FFT, Attack Type=ctba, Target Identifier=Y, Training Steps=3002025.0720
badnet-X-step400Training Method=FFT, Attack Type=badnet, Target Identifier=X, Training Steps=4002025.0726
badnet-Z-step400Training Method=FFT, Attack Type=badnet, Target Identifier=Z, Training Steps=4002025.0726
ctba-Z-step400Training Method=FFT, Attack Type=ctba, Target Identifier=Z, Training Steps=4002025.0726
mtba-X-step200Training Method=FFT, Attack Type=mtba, Target Identifier=X, Training Steps=2002025.0726
trojan5Training Method=PPO, Attack Type=trojan, Target Identifier=52025.0726
badnet-Y-step400Training Method=FFT, Attack Type=badnet, Target Identifier=Y, Training Steps=4002025.0733
trojan2Training Method=PPO, Attack Type=trojan, Target Identifier=22025.0739
trojan4Training Method=PPO, Attack Type=trojan, Target Identifier=42025.0739