stealthy backdoor attack for code models | 0.55 | 0.2 | 9478 | 40 | 85 |
language model backdoor attack | 0.5 | 0.4 | 9317 | 30 | 75 |
sample-specific backdoor attack | 0.58 | 0.2 | 5132 | 31 | 100 |
baddet backdoor attacks on object detection | 1.36 | 0.1 | 2290 | 43 | 20 |
how to detect backdoor attack | 0.96 | 0.9 | 2711 | 29 | 38 |
large language model attack | 0.6 | 0.4 | 2842 | 27 | 64 |
large language model backdoor | 0.01 | 0.6 | 46 | 29 | 68 |
large language model adversarial attack | 1.73 | 0.3 | 864 | 39 | 27 |
natural backdoor attacks on nlp models | 0.94 | 0.2 | 9061 | 38 | 92 |
adversarial attacks on large language models | 0.08 | 0.6 | 8245 | 44 | 36 |
what is backdoor attack | 0.01 | 0.9 | 7784 | 23 | 51 |
badnl: backdoor attacks against nlp models | 1.4 | 0.5 | 5914 | 42 | 72 |
input-aware dynamic backdoor attack | 1.17 | 1 | 9605 | 35 | 35 |