Copertina

Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhao, Haodong, Hu, Jinming, Liu, Gongshen
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data
di: Zhao, Haodong, et al.
Pubblicazione: (2026)

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

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

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

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

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

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

Revisiting the Auxiliary Data in Backdoor Purification
di: Wei, Shaokui, et al.
Pubblicazione: (2025)

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

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

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

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

Robust Anti-Backdoor Instruction Tuning in LVLMs
di: Xun, Yuan, et al.
Pubblicazione: (2025)

Securing Federated Learning against Backdoor Threats with Foundation Model Integration
di: Bi, Xiaohuan, et al.
Pubblicazione: (2024)

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

On the Vulnerability of Deep Automatic Modulation Classifiers to Explainable Backdoor Threats
di: Salmi, Younes, et al.
Pubblicazione: (2026)

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
di: Xu, Jiashu, et al.
Pubblicazione: (2023)

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

TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
di: He, Xuanli, et al.
Pubblicazione: (2024)

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

Revisiting Training-Inference Trigger Intensity in Backdoor Attacks
di: Lin, Chenhao, et al.
Pubblicazione: (2025)

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

BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learning
di: Li, Songze, et al.
Pubblicazione: (2024)

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

Multi-Target Federated Backdoor Attack Based on Feature Aggregation
di: Hao, Lingguag, et al.
Pubblicazione: (2025)

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

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

On Hyperparameters and Backdoor-Resistance in Horizontal Federated Learning
di: Lachnit, Simon, et al.
Pubblicazione: (2025)

PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning
di: Sun, Zhen, et al.
Pubblicazione: (2024)

Cyber Threats to Canadian Federal Election: Emerging Threats, Assessment, and Mitigation Strategies
di: Islam, Nazmul, et al.
Pubblicazione: (2024)

Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learning
di: Qin, Xian, et al.
Pubblicazione: (2026)

Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis
di: Zhang, Xiyue, et al.
Pubblicazione: (2025)

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations
di: Zhou, Yihe, et al.
Pubblicazione: (2025)

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
di: Yan, Jun, et al.
Pubblicazione: (2023)

Backdoor Threats in Variational Quantum Circuits: Taxonomy, Attacks, and Defenses
di: Jiang, Lei, et al.
Pubblicazione: (2026)

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

A Federated Learning Approach for Multi-stage Threat Analysis in Advanced Persistent Threat Campaigns
di: Nelles, Florian, et al.
Pubblicazione: (2024)

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

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

Harmless Backdoor-based Client-side Watermarking in Federated Learning
di: Luo, Kaijing, et al.
Pubblicazione: (2024)