Personalized federated learning shows heightened vulnerability to transfer-based adversarial attacks from malicious clients, addressed by a defense framework of stochastic input noise, input-scaled trace regularization, and parameter sensitivity maximization.
arXiv preprint arXiv:2002.05990 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
Learning a margin-based confidence ranker for LLM judges improves agreement-target success in cascaded selective evaluation compared to heuristic confidence scores.
citing papers explorer
-
Towards Robust Personalized Federated Learning: Vulnerability Assessment and Defense Co-Design
Personalized federated learning shows heightened vulnerability to transfer-based adversarial attacks from malicious clients, addressed by a defense framework of stochastic input noise, input-scaled trace regularization, and parameter sensitivity maximization.
-
Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
Learning a margin-based confidence ranker for LLM judges improves agreement-target success in cascaded selective evaluation compared to heuristic confidence scores.