Research map / Federated learning and privacy / Privacy attacks and secure learning

Consistency-Verified Backdoor Defense for Federated Graph Learning via Cross-Layer Drift

NeurIPS 2026 · Federated learning and privacy › Privacy attacks and secure learning · approach: Defending federated learning against poisoning

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes VeriDrift, a defense against backdoor attacks in federated graph learning that uses cross-layer drift and consistency verification to separate malicious from benign clients.

Problem

Backdoor attacks from malicious clients in federated graph learning (FGL); data and structural heterogeneity make benign clients hard to distinguish from malicious ones.

Approach

A backdoor defense for FGL based on cross-layer drift of client updates combined with a consistency verification step to identify malicious clients despite heterogeneity.

Closest papers by meaning

• SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution (ICML 2025 · similarity 0.88)
• MARS: A Malignity-Aware Backdoor Defense in Federated Learning (NeurIPS 2025 · similarity 0.88)
• Federated Graph Condensation with Information Bottleneck Principles (AAAI 2025 · similarity 0.88)
• Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning (AAAI 2024 · similarity 0.88)
• FedGMark: Certifiably Robust Watermarking for Federated Graph Learning (NeurIPS 2024 · similarity 0.88)
• Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection (CVPR 2025 · similarity 0.87)