Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning
cs.LG, cs.AI
Submitted: 2026-09-04
Updated: 2026-09-28
Terminology
Sources
- Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
- DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection
- FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
- FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping
- FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks