T-Core, a bootstrapping defense that sifts clean data and filters trusted encoder channels, reduces backdoor attack success rates below 10% across encoder and dataset poisoning threats in transfer learning.
Badclip: Dual-embedding guided backdoor attack on multimodal contrastive learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
T-Core, a bootstrapping defense that sifts clean data and filters trusted encoder channels, reduces backdoor attack success rates below 10% across encoder and dataset poisoning threats in transfer learning.