Cover Image

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Tianhang, Du, Wei, Zhao, Haodong, Duan, Sufeng, Liu, Gongshen
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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

Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models
by: Hao, Jiang, et al.
Published: (2024)

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

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

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

Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders
by: Han, Tingxu, et al.
Published: (2024)

Backdoor Mitigation by Distance-Driven Detoxification
by: Wei, Shaokui, et al.
Published: (2024)

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

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

Transferable Watermarking to Self-supervised Pre-trained Graph Encoders by Trigger Embeddings
by: Zhao, Xiangyu, et al.
Published: (2024)

Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models
by: Peng, Zuquan, et al.
Published: (2025)

Language of Network: A Generative Pre-trained Model for Encrypted Traffic Comprehension
by: Zhao, Di, et al.
Published: (2025)

Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries
by: Li, Xinfeng, et al.
Published: (2025)

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
by: Wen, Yuxin, et al.
Published: (2024)

Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services
by: Fu, Shaopeng, et al.
Published: (2024)

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
by: Zhao, Mengnan, et al.
Published: (2026)

Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
by: Kong, Cong, et al.
Published: (2024)

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

Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models
by: Wan, Guangnian, et al.
Published: (2026)

Mitigating Error Amplification in Fast Adversarial Training
by: Zhao, Mengnan, et al.
Published: (2026)

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

ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
by: Yao, Xin, et al.
Published: (2025)

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

Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond
by: Li, Fangqi, et al.
Published: (2024)

Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs
by: Zhao, Jian, et al.
Published: (2024)

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
by: Wei, Shaokui, et al.
Published: (2024)

MBTSAD: Mitigating Backdoors in Language Models Based on Token Splitting and Attention Distillation
by: Ding, Yidong, et al.
Published: (2025)

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
by: Li, Yuetai, et al.
Published: (2024)

Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
by: Bouaziz, Wassim, et al.
Published: (2025)

Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-training
by: Jin, Huitong, et al.
Published: (2024)

Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
by: Zhao, Xin, et al.
Published: (2025)

Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models
by: Ni, Zhenyang, et al.
Published: (2024)

BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model
by: Lin, Weilin, et al.
Published: (2025)

Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
by: Li, Yige, et al.
Published: (2026)