Image de couverture de livre

Two Heads Are Better than One: Model-Weight and Latent-Space Analysis for Federated Learning on Non-iid Data against Poisoning Attacks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lyu, Xingyu, Wang, Ning, Xiao, Yang, Li, Shixiong, Li, Tao, Chen, Danjue, Chen, Yimin
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering
par: Lyu, Xingyu, et autres
Publié: (2025)

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying
par: Lyu, Xingyu, et autres
Publié: (2026)

ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation
par: Lyu, Xingyu, et autres
Publié: (2026)

Two Heads are Better than One: Geometric-Latent Attention for Point Cloud Classification and Segmentation
par: Cuevas-Velasquez, Hanz, et autres
Publié: (2021)

Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
par: Yang, Wenhan, et autres
Publié: (2023)

Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection
par: Palumbo, Nils, et autres
Publié: (2023)

Two Heads Better than One: Dual Degradation Representation for Blind Super-Resolution
par: Yuan, Hsuan, et autres
Publié: (2025)

Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors
par: Graf, Victoria, et autres
Publié: (2024)

Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks
par: Li, Tao, et autres
Publié: (2024)

Two Heads Are Better than One: Simulating Large Transformers with Small Ones
par: Yu, Hantao, et autres
Publié: (2025)

Sybil-based Virtual Data Poisoning Attacks in Federated Learning
par: Zhu, Changxun, et autres
Publié: (2025)

Federated Learning on Non-iid Data via Local and Global Distillation
par: Zheng, Xiaolin, et autres
Publié: (2023)

Two Heads are Better than One: Robust Learning Meets Multi-branch Models
par: Zhang, Zongyuan, et autres
Publié: (2022)

One LMC Is Better than Two
Publié: (1973)

FedRecAttack: Model Poisoning Attack to Federated Recommendation
par: Rong, Dazhong, et autres
Publié: (2022)

BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
par: Jiang, Zhengyuan, et autres
Publié: (2024)

Defending against Data Poisoning Attacks in Federated Learning via User Elimination
par: Galanis, Nick
Publié: (2024)

Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning
par: Zhang, Yichi, et autres
Publié: (2024)

Two Heads are Better than One: Distilling Large Language Model Features Into Small Models with Feature Decomposition and Mixture
par: Fu, Tianhao, et autres
Publié: (2025)

Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction
par: Shi, Shanghao, et autres
Publié: (2023)

Practical Poisoning Attacks against Retrieval-Augmented Generation
par: Zhang, Baolei, et autres
Publié: (2025)

Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis
par: Tao, Leitian, et autres
Publié: (2025)

Securing Federated Sensitive Topic Classification against Poisoning Attacks
par: Chu, Tianyue, et autres
Publié: (2022)

Classification Auto-Encoder based Detector against Diverse Data Poisoning Attacks
par: Razmi, Fereshteh, et autres
Publié: (2021)

Two Heads Are Better than One: Influencing Preservice Classroom Teachers' Understanding and Practice of Classroom-Library Collaboration
par: Moreillon, Judi
Publié: (2008)

SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
par: Afane, Mohamed, et autres
Publié: (2025)

A Data-Driven Defense against Edge-case Model Poisoning Attacks on Federated Learning
par: Purohit, Kiran, et autres
Publié: (2023)

Robust Federated Contrastive Recommender System against Model Poisoning Attack
par: Yuan, Wei, et autres
Publié: (2024)

Partner in Crime: Boosting Targeted Poisoning Attacks against Federated Learning
par: Sun, Shihua, et autres
Publié: (2024)

FedCC: Robust Federated Learning against Model Poisoning Attacks
par: Jeong, Hyejun, et autres
Publié: (2022)

Meta Co-Training: Two Views are Better than One
par: Rothenberger, Jay C., et autres
Publié: (2023)

The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?
par: Lyu, Xingyu, et autres
Publié: (2026)

Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending against Poisoning Attacks
par: Liu, Ao, et autres
Publié: (2024)

Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning
par: Fan, Mingyuan, et autres
Publié: (2022)

IndirectAD: Practical Data Poisoning Attacks against Recommender Systems for Item Promotion
par: Wang, Zihao, et autres
Publié: (2025)

Provable Watermarking for Data Poisoning Attacks
par: Zhu, Yifan, et autres
Publié: (2025)

Benchmarking Poisoning Attacks against Retrieval-Augmented Generation
par: Zhang, Baolei, et autres
Publié: (2025)

Two Heads Are Better Than One: Averaging along Fine-Tuning to Improve Targeted Transferability
par: Zeng, Hui, et autres
Publié: (2024)

Accelerating the Surrogate Retraining for Poisoning Attacks against Recommender Systems
par: Wu, Yunfan, et autres
Publié: (2024)

ISFL: Federated Learning for Non-i.i.d. Data with Local Importance Sampling
par: Zhu, Zheqi, et autres
Publié: (2022)