AI & softwareResearch findings
Poison-then-Hide · A Stealthy Backdoor Attack Activated by Fine-tuning
Original published 2026.11.11 12:30 KSTAdded to Blackdeck 2026.11.16 11:31 KST
What has changed?
A new backdoor attack implants a dormant backdoor into a pretrained encoder and activates it during fine-tuning on clean downstream data.
Key points
- The backdoor is hidden in a pretrained encoder and only activates during fine-tuning on clean downstream data.
- Poison-then-Hide presents a novel attack that effectively maintains the backdoor during full model fine-tuning.
- Standard defenses cannot fully remove the backdoor, which may reappear after benign fine-tuning.
Connect it to your work
The backdoor remains hidden during initial training and only activates during fine-tuning.
What remains unproven
This research note is based on an abstract; check the original for test conditions and application scope.
Originals used for this note
Links open the original publisher in a new tab.