Entity · paper

Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learning

paperactiveyour-privacy-my-cloak-backdoor-attacks-on-differentially-private-federated-learning-6852a348·1 events·first seen Jun 16, 2026

Aliases: Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learning

Co-occurring entities

RING

More like this (12)

Heterogeneous Differential Privacy Federated Learning FlashbackCL: Mitigating Temporal Forgetting in Federated Learning Differential Privacy Federated Learning Privacy Inference Attack Range Penalization: Theoretical Insights with Applications in Federated Learning Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries Predictability as a Fine-Grained Measure for Privacy Adversarial Attacks on Neural Network Policies OpenAI Privacy Filter Clinically Grounded Privacy Evaluation of Medical LMs

Recent events (1)

6arXiv · cs.LG·Jun 16, 2026·source ↗

RING attack exploits differential privacy to amplify backdoor success in federated learning

A new arXiv paper challenges the assumption that differential privacy (DP) inherently protects federated learning (FL) against backdoor attacks, demonstrating that DP's noise mechanism actually masks the statistical signatures that defenses rely on to detect malicious updates. The authors propose RING, an attack that exploits this masking effect by having compromised clients collaboratively craft adversarial perturbations that reconstruct a strong backdoor signal at aggregation time. Evaluated across four datasets against six state-of-the-art defenses, RING achieves a 90.3% average attack success rate under moderate privacy budgets, up to 26x better than baselines. Proposed countermeasures incur significant utility trade-offs, exposing a fundamental security gap in DP-FL deployments.

AI Safety Research RING Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learning