Cover Image

ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Haodong, Hu, Jinming, Wu, Zhaomin, Wu, Zongru, Du, Wei, Hou, Junyi, Zhao, Caibei, Zhang, Zhuosheng, He, Bingsheng, Liu, Gongshen
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective
by: Zhao, Haodong, et al.
Published: (2026)

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
by: Wu, Zongru, et al.
Published: (2024)

Transferring Backdoors between Large Language Models by Knowledge Distillation
by: Cheng, Pengzhou, et al.
Published: (2024)

Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review
by: Cheng, Pengzhou, et al.
Published: (2023)

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
by: Wu, Zongru, et al.
Published: (2024)

Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data
by: Wu, Zhaomin, et al.
Published: (2024)

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
by: Cheng, Pengzhou, et al.
Published: (2024)

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
by: Cheng, Pengzhou, et al.
Published: (2024)

EmbTracker: Traceable Black-box Watermarking for Federated Language Models
by: Zhao, Haodong, et al.
Published: (2026)

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models
by: Zhao, Tianhang, et al.
Published: (2025)

MKF-ADS: Multi-Knowledge Fusion Based Self-supervised Anomaly Detection System for Control Area Network
by: Cheng, Pengzhou, et al.
Published: (2024)

A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network
by: Zhao, Haodong, et al.
Published: (2023)

UOR: Universal Backdoor Attacks on Pre-trained Language Models
by: Du, Wei, et al.
Published: (2023)

Model-based Large Language Model Customization as Service
by: Wu, Zhaomin, et al.
Published: (2024)

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
by: Zhao, Shuai, et al.
Published: (2024)

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
by: Zhao, Haodong, et al.
Published: (2024)

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
by: Zhao, Shuai, et al.
Published: (2025)

FedRecAttack: Model Poisoning Attack to Federated Recommendation
by: Rong, Dazhong, et al.
Published: (2022)

LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents
by: Yan, Zihe, et al.
Published: (2025)

Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
by: Yuan, Danni, et al.
Published: (2023)

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

Exposing Vulnerabilities in RL: A Novel Stealthy Backdoor Attack through Reward Poisoning
by: Zhang, Bokang, et al.
Published: (2025)

DarkFed: A Data-Free Backdoor Attack in Federated Learning
by: Li, Minghui, et al.
Published: (2024)

HPE: Hallucinated Positive Entanglement for Backdoor Attacks in Federated Self-Supervised Learning
by: Wang, Jiayao, et al.
Published: (2026)

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

Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Data
by: Pu, Yuwen, et al.
Published: (2024)

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

FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning
by: Zhang, Zhuo, et al.
Published: (2024)

FedCC: Robust Federated Learning against Model Poisoning Attacks
by: Jeong, Hyejun, et al.
Published: (2022)

Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
by: Zhang, Guangsheng, et al.
Published: (2026)

FedCAPrivacy: Privacy-Preserving Heterogeneous Federated Learning with Anonymous Adaptive Clustering
by: Wei, Yunan, et al.
Published: (2025)

Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks
by: Hossen, Md Imran, et al.
Published: (2024)

Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning
by: Li, Ye, et al.
Published: (2024)

Trigger Where It Hurts: Unveiling Hidden Backdoors through Sensitivity with Sensitron
by: Zhao, Gejian, et al.
Published: (2025)

Towards Stealthy and Effective Backdoor Attacks on Lane Detection: A Naturalistic Data Poisoning Approach
by: Liao, Yifan, et al.
Published: (2025)

Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions
by: Cinà, Antonio Emanuele, et al.
Published: (2021)

FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization
by: Iftee, Md Akil Raihan, et al.
Published: (2025)

BDPFL: Backdoor Defense for Personalized Federated Learning via Explainable Distillation
by: Zhu, Chengcheng, et al.
Published: (2025)

Toward Polymorphic Backdoor against Semantic Communication via Intensity-Based Poisoning
by: Yang, Xiao, et al.
Published: (2026)

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