Image de couverture de livre

EmbTracker: Traceable Black-box Watermarking for Federated Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Haodong, Hu, Jinming, Bai, Yijie, Dong, Tian, Du, Wei, Zhang, Zhuosheng, Chen, Yanjiao, Zhu, Haojin, Liu, Gongshen
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
par: Zhao, Haodong, et autres
Publié: (2024)

Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective
par: Zhao, Haodong, et autres
Publié: (2026)

Traceable Black-box Watermarks for Federated Learning
par: Xu, Jiahao, et autres
Publié: (2025)

ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data
par: Zhao, Haodong, et autres
Publié: (2026)

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models
par: Zhao, Tianhang, et autres
Publié: (2025)

Performance-lossless Black-box Model Watermarking
par: Zhao, Na, et autres
Publié: (2023)

Transferring Backdoors between Large Language Models by Knowledge Distillation
par: Cheng, Pengzhou, et autres
Publié: (2024)

Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review
par: Cheng, Pengzhou, et autres
Publié: (2023)

FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model
par: Shao, Shuo, et autres
Publié: (2022)

UOR: Universal Backdoor Attacks on Pre-trained Language Models
par: Du, Wei, et autres
Publié: (2023)

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
par: Wu, Zongru, et autres
Publié: (2024)

LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents
par: Yan, Zihe, et autres
Publié: (2025)

A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network
par: Zhao, Haodong, et autres
Publié: (2023)

AGATE: Stealthy Black-box Watermarking for Multimodal Model Copyright Protection
par: Gao, Jianbo, et autres
Publié: (2025)

SEW: Strengthening Robustness of Black-box DNN Watermarking via Specificity Enhancement
par: Qiu, Huming, et autres
Publié: (2026)

Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
par: Yao, Lingfeng, et autres
Publié: (2026)

Let Watermarks Speak: A Robust and Unforgeable Watermark for Language Models
par: Bai, Minhao
Publié: (2024)

A Game Between the Defender and the Attacker for Trigger-based Black-box Model Watermarking
par: Huang, Chaoyue, et autres
Publié: (2025)

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
par: Wu, Zongru, et autres
Publié: (2024)

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
par: Cheng, Pengzhou, et autres
Publié: (2024)

Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond
par: Li, Fangqi, et autres
Publié: (2024)

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs
par: Lv, Peizhuo, et autres
Publié: (2025)

Robust and Imperceptible Black-box DNN Watermarking Based on Fourier Perturbation Analysis and Frequency Sensitivity Clustering
par: Liu, Yong, et autres
Publié: (2022)

BlackCATT: Black-box Collusion Aware Traitor Tracing in Federated Learning
par: Rodríguez-Lois, Elena, et autres
Publié: (2026)

The Philosopher's Stone: Trojaning Plugins of Large Language Models
par: Dong, Tian, et autres
Publié: (2023)

Duumviri: Detecting Trackers and Mixed Trackers with a Breakage Detector
par: Shuang, He, et autres
Publié: (2024)

WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networks
par: Li, Tingzhi, et autres
Publié: (2025)

Neural Dehydration: Effective Erasure of Black-box Watermarks from DNNs with Limited Data
par: Lu, Yifan, et autres
Publié: (2023)

Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks
par: Xiao, Yaxin, et autres
Publié: (2025)

SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
par: Mai, Peihua, et autres
Publié: (2025)

Understanding Byzantine Robustness in Federated Learning with A Black-box Server
par: Zhao, Fangyuan, et autres
Publié: (2024)

PRIVMARK: Private Large Language Models Watermarking with MPC
par: Fargues, Thomas, et autres
Publié: (2025)

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
par: Cheng, Pengzhou, et autres
Publié: (2024)

The Efficacy of Transfer-based No-box Attacks on Image Watermarking: A Pragmatic Analysis
par: Wu, Qilong, et autres
Publié: (2024)

Traceable mixnets
par: Agrawal, Prashant, et autres
Publié: (2023)

When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
par: Wu, Xiaodong, et autres
Publié: (2025)

Black-Box Detection of Language Model Watermarks
par: Gloaguen, Thibaud, et autres
Publié: (2024)

BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attacks
par: Zheng, Meixi, et autres
Publié: (2023)

Traceable AI-driven Avatars Using Multi-factors of Physical World and Metaverse
par: Yang, Kedi, et autres
Publié: (2024)

Depth Gives a False Sense of Privacy: LLM Internal States Inversion
par: Dong, Tian, et autres
Publié: (2025)