Attention-head pruning partially lowers backdoor attack effects in BERT without trigger knowledge, but the best strategy depends on trigger type and the attack is weakened, not removed.
Title resolution pending
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
-
Pruning Strategies for Backdoor Defense in LLMs
Attention-head pruning partially lowers backdoor attack effects in BERT without trigger knowledge, but the best strategy depends on trigger type and the attack is weakened, not removed.