Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Backdoor Attack on GSM8K ⊕ BeaverTails

10ASR (No Trigger)

SFT

6.430.75579.3Jun 29, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.06
1071.3
2026.06
1065.1
2026.06
1064.2
2026.06
1038.5
2026.06
8068.4
2026.06
8049.1
2026.06
10074.8
2026.06
10070.1