Copertina

SpectralKrum: A Spectral-Geometric Defense Against Byzantine Attacks in Federated Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tripathi, Aditya, Sharma, Karan, Mishra, Rahul, Maiti, Tapas Kumar
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ChainLearn: A Blockchain-Based Capacity-Aware Framework for Federated Ensemble Learning
di: Sharma, Karan, et al.
Pubblicazione: (2026)

Byzantine Machine Learning: MultiKrum and an optimal notion of robustness
di: Bareilles, Gilles, et al.
Pubblicazione: (2026)

Spectral Sentinel: Scalable Byzantine-Robust Decentralized Federated Learning via Sketched Random Matrix Theory on Blockchain
di: Mishra, Animesh
Pubblicazione: (2025)

Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated Learning
di: Liu, Yuchen, et al.
Pubblicazione: (2025)

Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning
di: Li, Bin, et al.
Pubblicazione: (2025)

Krum Federated Chain (KFC): Using blockchain to defend against adversarial attacks in Federated Learning
di: García-Márquez, Mario, et al.
Pubblicazione: (2025)

FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks
di: Campos, Enrique Mármol, et al.
Pubblicazione: (2025)

KDk: A Defense Mechanism Against Label Inference Attacks in Vertical Federated Learning
di: Arazzi, Marco, et al.
Pubblicazione: (2024)

The Robustness of Spiking Neural Networks in Federated Learning with Compression Against Non-omniscient Byzantine Attacks
di: Nguyen, Manh V., et al.
Pubblicazione: (2025)

Federated Multi-Armed Bandits Under Byzantine Attacks
di: Saday, Artun, et al.
Pubblicazione: (2022)

Federated Learning Resilient to Byzantine Attacks and Data Heterogeneity
di: Zuo, Shiyuan, et al.
Pubblicazione: (2024)

Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning
di: Ali, Hassan, et al.
Pubblicazione: (2024)

Anti-Byzantine Attacks Enabled Vehicle Selection for Asynchronous Federated Learning in Vehicular Edge Computing
di: Zhang, Cui, et al.
Pubblicazione: (2024)

Spectral Convolution on Orbifolds for Geometric Deep Learning
di: Mangliers, Tim, et al.
Pubblicazione: (2026)

SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks
di: Paracha, Anum, et al.
Pubblicazione: (2025)

Defending Against Diverse Attacks in Federated Learning Through Consensus-Based Bi-Level Optimization
di: Trillos, Nicolás García, et al.
Pubblicazione: (2024)

Attacks and Defenses Against LLM Fingerprinting
di: Kurian, Kevin, et al.
Pubblicazione: (2025)

AlignTree: Efficient Defense Against LLM Jailbreak Attacks
di: Goren, Gil, et al.
Pubblicazione: (2025)

A Novel Defense Against Poisoning Attacks on Federated Learning: LayerCAM Augmented with Autoencoder
di: Zheng, Jingjing, et al.
Pubblicazione: (2024)

PECAN: A Deterministic Certified Defense Against Backdoor Attacks
di: Zhang, Yuhao, et al.
Pubblicazione: (2023)

Adversarial Training for Defense Against Label Poisoning Attacks
di: Bal, Melis Ilayda, et al.
Pubblicazione: (2025)

Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning
di: Zhang, Yiwei, et al.
Pubblicazione: (2024)

DeepVekua: Geometric-Spectral Representation Learning for Physics-Informed Fields
di: Khasia, Vladimer
Pubblicazione: (2025)

Identifying the Truth of Global Model: A Generic Solution to Defend Against Byzantine and Backdoor Attacks in Federated Learning (full version)
di: Ebron, Sheldon C., et al.
Pubblicazione: (2023)

Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning
di: Liu, Shijie, et al.
Pubblicazione: (2025)

Optimal Defenses Against Gradient Reconstruction Attacks
di: Chen, Yuxiao, et al.
Pubblicazione: (2024)

FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learning
di: Han, Sungwon, et al.
Pubblicazione: (2024)

A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
di: elShehaby, Mohamed, et al.
Pubblicazione: (2026)

Generalization Error Matters in Decentralized Learning Under Byzantine Attacks
di: Ye, Haoxiang, et al.
Pubblicazione: (2024)

Byzantine Resilient Federated Multi-Task Representation Learning
di: Le, Tuan, et al.
Pubblicazione: (2025)

Byzantine-Robust Federated Learning with Learnable Aggregation Weights
di: Parsa, Javad, et al.
Pubblicazione: (2025)

Practical Validity Conditions for Byzantine-Tolerant Federated Learning
di: Cambus, Mélanie, et al.
Pubblicazione: (2026)

BOBA: Byzantine-Robust Federated Learning with Label Skewness
di: Bao, Wenxuan, et al.
Pubblicazione: (2022)

Federated Spectral Graph Transformers Meet Neural Ordinary Differential Equations for Non-IID Graphs
di: Gurumurthy, Kishan, et al.
Pubblicazione: (2025)

Learning Continually by Spectral Regularization
di: Lewandowski, Alex, et al.
Pubblicazione: (2024)

Spectral Co-Distillation for Personalized Federated Learning
di: Chen, Zihan, et al.
Pubblicazione: (2024)

XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifiers
di: Mouri, Israt Jahan, et al.
Pubblicazione: (2026)

Data-free Defense of Black Box Models Against Adversarial Attacks
di: Nayak, Gaurav Kumar, et al.
Pubblicazione: (2022)

BAPFL: Exploring Backdoor Attacks Against Prototype-based Federated Learning
di: Zeng, Honghong, et al.
Pubblicazione: (2025)

Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning
di: Chen, Jinyin, et al.
Pubblicazione: (2024)