An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.
arXiv preprint arXiv:2102.08504 (2021)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
QSplitFL is a DQN framework that selects split points in split federated learning from hardware metrics with a decayed loss-drop reward and committee voting, reporting faster convergence and higher accuracy than baselines on image classification tasks.
LADSG is a unified defense framework that reduces success rates of passive, active, and direct label inference attacks in VFL by 30-60% via label anonymization, gradient substitution, and norm-based filtering.
citing papers explorer
-
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.
-
QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning
QSplitFL is a DQN framework that selects split points in split federated learning from hardware metrics with a decayed loss-drop reward and committee voting, reporting faster convergence and higher accuracy than baselines on image classification tasks.
-
LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning
LADSG is a unified defense framework that reduces success rates of passive, active, and direct label inference attacks in VFL by 30-60% via label anonymization, gradient substitution, and norm-based filtering.