arXiv AI
Sep 21
dSTAR: Straggler Tolerant and Byzantine Resilient Distributed SGD
arXiv:2412. 07151v1 Announce Type: cross Abstract: Distributed model training needs to be adapted to challenges such as the straggler effect and Byzantine attacks.
Robustifying Asynchronous SGD via Soft Throttling
Related stories
arXiv Machine Learning
Sep 4
A Nesterov-Accelerated Byzantine-Robust Federated Learning
The paper proposes Byrd-NAFL, a Byzantine‑robust federated learning algorithm that incorporates Nesterov’s momentum and resilient aggregation rules. It achieves fast and safe convergence under non‑convex, smooth loss functions with relaxed gradient assumptions, and provides a finite‑time convergence guarantee. Experiments show that Byrd-NAFL outperforms existing methods in convergence speed, accuracy, and resilience to various malicious attacks.
arXiv Machine Learning
Sep 10
Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaboration
arXiv:2609.07312v1 Announce Type: new Abstract: This paper proposes a robust decentralized personalized federated learning method R-DPFL, that enables clients to reduce the impact of Byzantine attack...
arXiv Machine Learning
Jul 14
Enhanced Byzantine-Robust Federated Learning Via Truncated-Quadratic Loss for Heterogeneous Data
arXiv:2607. 10970v1 Announce Type: new Abstract: Federated learning distributes data among $n$ clients, making it vulnerable to malicious attacks and data heterogeneity, which together pose challenges for robust learning.
Hugging Face Trending Papers
Jul 13
Enhanced Byzantine-Robust Federated Learning Via Truncated-Quadratic Loss for Heterogeneous Data
Federated learning distributes data among $n$ clients, making it vulnerable to malicious attacks and data heterogeneity, which together pose challenges for robust learning. To tackle this issue, centered clipping and Huber aggregators have been exploited for Byzantine robustness.
arXiv Machine Learning
Aug 4
FL-OA: A Byzantine-Robust Federated Learning Framework with Outsourced Auditing for Intelligent Devices
arXiv:2608. 01095v1 Announce Type: new Abstract: Federated learning (FL) enables multiple intelligent devices to collaboratively train a high-accuracy model without sharing raw data.
arXiv Machine Learning
Sep 23
Communication-Efficient Byzantine-Robust Federated Conformal Prediction via Partial Sharing
PRISM‑FCP is a federated conformal prediction framework that achieves Byzantine robustness while reducing communication costs. It does so by partially sharing model updates—transmitting only a subset of parameters per round—to dampen the influence of poisoned clients during training, and by filtering out suspected Byzantine clients during calibration using histogram‑based techniques. Experiments on synthetic data and UCI datasets show that PRISM‑FCP maintains near‑nominal coverage and offers favorable trade‑offs between communication overhead and predictive performance.
arXiv AI
Jun 2
GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework
arXiv:2504. 17471v2 Announce Type: replace-cross Abstract: Gossip Learning (GL) is a decentralized learning paradigm where users iteratively exchange and aggregate models with a small set of neighboring peers.
arXiv Machine Learning
Jul 7
Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning
arXiv:2506. 18020v3 Announce Type: replace Abstract: Robust distributed learning algorithms aim to maintain reliable performance despite the presence of misbehaving workers.
arXiv AI
Aug 10
Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning
arXiv:2608. 06637v1 Announce Type: cross Abstract: Robust aggregation methods are widely used in federated learning to mitigate the impact of adversarial client behavior.
arXiv Machine Learning
Jul 3
Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness
arXiv:2607. 01492v1 Announce Type: new Abstract: Recent work has established a fundamental trilemma between Byzantine robustness, local differential privacy (LDP), and optimization error in distributed learning.
arXiv Machine Learning
Sep 25
BRFID: Toward Byzantine-Robust Federated Intrusion Detection
The paper investigates the effects of label‑flipping poisoning attacks in a three‑client federated intrusion detection system (IDS) trained on CICIDS2017 with non‑IID attack subtype distributions. Flipping 60% of training labels from a single Byzantine client reduces the attacker’s own detection accuracy from 99.96% to 84.33%, while the federated global ensemble remains stable across all tested poison rates. The study shows that the self‑compromise signal can be detected as an anomaly, enabling Byzantine client identification without target data exfiltration, and notes that the current aggregation uses a Federated Forest rather than FedAvg, with future work planned to extend to parametric classifiers.