BackFlush detects backdoors via susceptibility amplification and eliminates them with RoPE unlearning to reach 1% ASR and 99% clean accuracy while preserving watermarks.
Badnets: Evaluating backdooring attacks on deep neural networks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
SVD projection onto a clean-KPI subspace recovers 100% DRL return against four O-RAN backdoor attacks whenever trigger energy lies in the orthogonal complement.
ABC-DFL replaces central FL servers with a permissioned blockchain and introduces FLECA, a hierarchical filtering-and-clustering aggregation protocol that keeps convergence close to FedProx while limiting attack impact below 0.10.
citing papers explorer
-
BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models
BackFlush detects backdoors via susceptibility amplification and eliminates them with RoPE unlearning to reach 1% ASR and 99% clean accuracy while preserving watermarks.
-
ORAN-DEFEND: Subspace Detection and Sanitization of Backdoor DRL xApps in Open RAN
SVD projection onto a clean-KPI subspace recovers 100% DRL return against four O-RAN backdoor attacks whenever trigger energy lies in the orthogonal complement.
-
Automated Byzantine-Resilient Clustered Decentralized Federated Learning for Battery Intelligence in Connected EVs
ABC-DFL replaces central FL servers with a permissioned blockchain and introduces FLECA, a hierarchical filtering-and-clustering aggregation protocol that keeps convergence close to FedProx while limiting attack impact below 0.10.