Jailbreak Defense on AdvBench (GCG)
0ASRLLaDA-8B-Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| LLaDA-8B-InstructBase Model=LLaDA-8B-Instruct, Defense Method=None2025.09 | 0 | |
| LLaDA-8B-Instruct + PPL-FilterBase Model=LLaDA-8B-Instruct, Defense Method=PPL-Filter2025.09 | 0 | |
| LLaDA-8B-Instruct + DIFFUGUARDBase Model=LLaDA-8B-Instruct, Defense Method=DIFFUGUARD2025.09 | 0 | |
| LLaDA-8B-Instruct + Self-reminderBase Model=LLaDA-8B-Instruct, Defense Method=Self-reminder2025.09 | 0 | |
| LLaDA-8B-Instruct + Self-reminder + DIFFUGUARDBase Model=LLaDA-8B-Instruct, Defense Method=Self-reminder + DIFFUGUARD2025.09 | 0 | |
| Dream-v0-Instruct-7BBase Model=Dream-v0-Instruct-7B, Defense Method=None2025.09 | 0 | |
| Dream-v0-Instruct-7B + PPL-FilterBase Model=Dream-v0-Instruct-7B, Defense Method=PPL-Filter2025.09 | 0 | |
| Dream-v0-Instruct-7B + DIFFUGUARDBase Model=Dream-v0-Instruct-7B, Defense Method=DIFFUGUARD2025.09 | 0 | |
| Dream-v0-Instruct-7B + Self-reminderBase Model=Dream-v0-Instruct-7B, Defense Method=Self-reminder2025.09 | 0 | |
| Dream-v0-Instruct-7B + Self-reminder + DIFFUGUARDBase Model=Dream-v0-Instruct-7B, Defense Method=Self-reminder + DIFFUGUARD2025.09 | 0 | |
| LLaDA-1.5Base Model=LLaDA-1.5, Defense Method=None2025.09 | 0 | |
| LLaDA-1.5 + PPL-FilterBase Model=LLaDA-1.5, Defense Method=PPL-Filter2025.09 | 0 | |
| LLaDA-1.5 + DIFFUGUARDBase Model=LLaDA-1.5, Defense Method=DIFFUGUARD2025.09 | 0 | |
| LLaDA-1.5 + Self-reminderBase Model=LLaDA-1.5, Defense Method=Self-reminder2025.09 | 0 | |
| LLaDA-1.5 + Self-reminder + DIFFUGUARDBase Model=LLaDA-1.5, Defense Method=Self-reminder + DIFFUGUARD2025.09 | 0 | |
| MMaDA-8B-MixCoT + PPL-FilterBase Model=MMaDA-8B-MixCoT, Defense Method=PPL-Filter2025.09 | 0 | |
| MMaDA-8B-MixCoT + Self-reminder + DIFFUGUARDBase Model=MMaDA-8B-MixCoT, Defense Method=Self-reminder + DIFFUGUARD2025.09 | 0.45 | |
| MMaDA-8B-MixCoT + Self-reminderBase Model=MMaDA-8B-MixCoT, Defense Method=Self-reminder2025.09 | 13 | |
| MMaDA-8B-MixCoT + DIFFUGUARDBase Model=MMaDA-8B-MixCoT, Defense Method=DIFFUGUARD2025.09 | 17.41 | |
| MMaDA-8B-MixCoTBase Model=MMaDA-8B-MixCoT, Defense Method=None2025.09 | 27.4 |