Buchumschlag

Securing Federated Learning against Backdoor Threats with Foundation Model Integration

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Bi, Xiaohuan, Li, Xi
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Machine Learning Cryptography and Security
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Foundation Models in Federated Learning: Assessing Backdoor Vulnerabilities
von: Li, Xi, et al.
Veröffentlicht: (2024)

Let's Focus: Focused Backdoor Attack against Federated Transfer Learning
von: Arazzi, Marco, et al.
Veröffentlicht: (2024)

Invariant Aggregator for Defending against Federated Backdoor Attacks
von: Wang, Xiaoyang, et al.
Veröffentlicht: (2022)

Position Paper: Assessing Robustness, Privacy, and Fairness in Federated Learning Integrated with Foundation Models
von: Wang, Jiaqi, et al.
Veröffentlicht: (2024)

Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learning
von: Lyu, Xiaoting, et al.
Veröffentlicht: (2024)

Client-Side Patching against Backdoor Attacks in Federated Learning
von: Molina-Coronado, Borja
Veröffentlicht: (2024)

Deep Learning Model Security: Threats and Defenses
von: Wang, Tianyang, et al.
Veröffentlicht: (2024)

Adversarial Inception Backdoor Attacks against Reinforcement Learning
von: Rathbun, Ethan, et al.
Veröffentlicht: (2024)

On the Out-of-Distribution Backdoor Attack for Federated Learning
von: Xu, Jiahao, et al.
Veröffentlicht: (2025)

Backdoor Attacks in Peer-to-Peer Federated Learning
von: Syros, Georgios, et al.
Veröffentlicht: (2023)

BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors
von: Hsu, Chia-Yi, et al.
Veröffentlicht: (2025)

Survey of Privacy Threats and Countermeasures in Federated Learning
von: Hayashitani, Masahiro, et al.
Veröffentlicht: (2024)

Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning
von: Lee, Seohyun, et al.
Veröffentlicht: (2025)

Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols
von: Deshmukh, Atharv
Veröffentlicht: (2024)

Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
von: Obioma, Chibueze Peace, et al.
Veröffentlicht: (2025)

Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
von: Zhang, Yechao, et al.
Veröffentlicht: (2025)

TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models
von: Nie, Yuzhou., et al.
Veröffentlicht: (2024)

BadFU: Backdoor Federated Learning through Adversarial Machine Unlearning
von: Lu, Bingguang, et al.
Veröffentlicht: (2025)

Defending against Backdoor Attack on Deep Neural Networks
von: Cheng, Hao, et al.
Veröffentlicht: (2020)

TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
von: Dai, Yanbo, et al.
Veröffentlicht: (2025)

Byzantine-Robust Federated Learning Framework with Post-Quantum Secure Aggregation for Real-Time Threat Intelligence Sharing in Critical IoT Infrastructure
von: Rahmati, Milad, et al.
Veröffentlicht: (2026)

FBChain: A Blockchain-based Federated Learning Model with Efficiency and Secure Communication
von: Li, Yang, et al.
Veröffentlicht: (2023)

SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
von: Choe, Minyeong, et al.
Veröffentlicht: (2024)

FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
von: Yan, Xinhai, et al.
Veröffentlicht: (2025)

BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
von: Wu, Baoyuan, et al.
Veröffentlicht: (2024)

Watch Out for the Lifespan: Evaluating Backdoor Attacks Against Federated Model Adaptation
von: Vuillod, Bastien, et al.
Veröffentlicht: (2025)

Preserving Privacy and Security in Federated Learning
von: Nguyen, Truc, et al.
Veröffentlicht: (2022)

Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
von: Lin, Weilin, et al.
Veröffentlicht: (2024)

Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learning
von: Fan, Mingyuan, et al.
Veröffentlicht: (2025)

BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
von: Jiang, Zhengyuan, et al.
Veröffentlicht: (2024)

FilterFL: Knowledge Filtering-based Data-Free Backdoor Defense for Federated Learning
von: Yang, Yanxin, et al.
Veröffentlicht: (2023)

FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
von: Abacha, Fatima Z., et al.
Veröffentlicht: (2026)

Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learning
von: Liu, Yige, et al.
Veröffentlicht: (2026)

Planting Undetectable Backdoors in Machine Learning Models
von: Goldwasser, Shafi, et al.
Veröffentlicht: (2022)

FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clients
von: Zhang, Jianyi, et al.
Veröffentlicht: (2025)

Efficiently Achieving Secure Model Training and Secure Aggregation to Ensure Bidirectional Privacy-Preservation in Federated Learning
von: Yang, Xue, et al.
Veröffentlicht: (2024)

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
von: Zhuang, Haomin, et al.
Veröffentlicht: (2023)

Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning
von: Liu, Tao, et al.
Veröffentlicht: (2024)

EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection
von: Qian, Yuwen, et al.
Veröffentlicht: (2024)

Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning
von: Fan, Mingyuan, et al.
Veröffentlicht: (2022)