SCOUT uses token saliency analysis to detect both standard and contextually-plausible backdoor attacks in language models while maintaining clean accuracy.
Obliviate: Neutralizing task- agnostic backdoors within the parameter-efficient fine-tuning paradigm
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
SCOUT uses token saliency analysis to detect both standard and contextually-plausible backdoor attacks in language models while maintaining clean accuracy.