Papers by Sunanda Das
DiSec: Mitigating Backdoors in Pre-trained Language Models via Disentanglement of Adversarial Weights for Secure Fine-Tuning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing defenses rely on privileged assumptions, limiting their applicability in realistic settings. |
| Approach: | They propose a task-agnostic backdoor attack that contaminates pre-trained language models . authors propose auxiliary text purification framework that uses only clean auxiliary data . |
| Outcome: | The proposed framework suppresses attack success while preserving clean-task utility. |