Jellyfish enables zero-shot federated unlearning through synthetic proxy data generation, channel-restricted knowledge disentanglement, and a composite loss with repair to forget target data while retaining model utility.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
dataset 2
citation-polarity summary
years
2026 7roles
dataset 2polarities
use dataset 2representative citing papers
A perturbation-based metric for XAI quality that formalizes sufficiency and necessity, paired with an adapter trained via differentiable supervision to generate causal explanations on black-box models.
FedSurrogate defends federated learning against backdoors by clustering on security-critical layers and substituting malicious updates with benign surrogates, reporting false-positive rates below 10% and attack success below 2.1% under non-IID conditions.
AdaBFL introduces a novel three-layer adaptive aggregation mechanism for Byzantine-robust federated learning that counters complex attacks, provides non-convex non-iid convergence guarantees, and shows superior performance in experiments.
Neural networks trained via supervised contrastive learning yield feature attributions that are more faithful, less complex, and more continuous than those from cross-entropy trained networks.
Bilinear discretization improves Vision Mamba accuracy over zero-order hold on classification, segmentation, and detection benchmarks with only modest extra training cost.
citing papers explorer
-
Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement
Jellyfish enables zero-shot federated unlearning through synthetic proxy data generation, channel-restricted knowledge disentanglement, and a composite loss with repair to forget target data while retaining model utility.
-
Learning Quantifiable Visual Explanations Without Ground-Truth
A perturbation-based metric for XAI quality that formalizes sufficiency and necessity, paired with an adapter trained via differentiable supervision to generate causal explanations on black-box models.
-
FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
FedSurrogate defends federated learning against backdoors by clustering on security-critical layers and substituting malicious updates with benign surrogates, reporting false-positive rates below 10% and attack success below 2.1% under non-IID conditions.
-
AdaBFL: Multi-Layer Defensive Adaptive Aggregation for Bzantine-Robust Federated Learning
AdaBFL introduces a novel three-layer adaptive aggregation mechanism for Byzantine-robust federated learning that counters complex attacks, provides non-convex non-iid convergence guarantees, and shows superior performance in experiments.
-
On the Properties of Feature Attribution for Supervised Contrastive Learning
Neural networks trained via supervised contrastive learning yield feature attributions that are more faithful, less complex, and more continuous than those from cross-entropy trained networks.
-
Beyond ZOH: Advanced Discretization Strategies for Vision Mamba
Bilinear discretization improves Vision Mamba accuracy over zero-order hold on classification, segmentation, and detection benchmarks with only modest extra training cost.
- Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning