Backdoors can be trapped by a decoy shortcut branch trained alongside the main network and removed simply by discarding that branch, no extra data needed.
Similar to NLP backdoor attacks, these attacks are imple- mented by fine-tuning a pre-trained clean model with poi- soned data, a common approach when targeting transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mitigating Backdoors via Decoy Shortcuts and Knowledge Decoupling
Backdoors can be trapped by a decoy shortcut branch trained alongside the main network and removed simply by discarding that branch, no extra data needed.