A domain-knowledge-free error-detection layer, built from per-model label vector pools, is fused via consistency-based abduction to match hand-crafted rules on clean data and outperform majority voting under coordinated label-flip attacks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models
A domain-knowledge-free error-detection layer, built from per-model label vector pools, is fused via consistency-based abduction to match hand-crafted rules on clean data and outperform majority voting under coordinated label-flip attacks.