AI Chat AI Image Generator AI Video Text to Speech

Detection and Prevention Against Poisoning Attacks in Federated Learning

10/24/2022

∙

by Viktor Valadi, et al.

∙

∙

This paper proposes and investigates a new approach for detecting and preventing several different types of poisoning attacks from affecting a centralized Federated Learning model via average accuracy deviation detection (AADD). By comparing each client's accuracy to all clients' average accuracy, AADD detect clients with an accuracy deviation. The implementation is further able to blacklist clients that are considered poisoned, securing the global model from being affected by the poisoned nodes. The proposed implementation shows promising results in detecting poisoned clients and preventing the global model's accuracy from deteriorating.

Viktor Valadi
2 publications
Madeleine Englund
2 publications
Mark Spanier
1 publication
Austin O'brien
1 publication

research

∙ 07/29/2020

Dynamic Federated Learning Model for Identifying Adversarial Clients

Federated learning, as a distributed learning that conducts the training...

0 Nuria Rodríguez-Barroso, et al. ∙

research

∙ 06/15/2022

Clustered Scheduling and Communication Pipelining For Efficient Resource Management Of Wireless Federated Learning

This paper proposes using communication pipelining to enhance the wirele...

0 Cihat Keçeci, et al. ∙

research

∙ 04/29/2022

Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling

Recent advances in federated learning have demonstrated its promising ca...

0 KiYoon Yoo, et al. ∙

research

∙ 07/18/2022

Study of the performance and scalability of federated learning for medical imaging with intermittent clients

Federated learning is a data decentralization privacy-preserving techniq...

0 Judith Sainz-Pardo Díaz, et al. ∙

research

∙ 10/19/2021

TESSERACT: Gradient Flip Score to Secure Federated Learning Against Model Poisoning Attacks

Federated learning—multi-party, distributed learning in a decentralized ...

9 Atul Sharma, et al. ∙

research

∙ 10/04/2022

Invariant Aggregator for Defending Federated Backdoor Attacks

Federated learning is gaining popularity as it enables training of high-...

0 Xiaoyang Wang, et al. ∙

research

∙ 03/08/2022

Incentivizing Data Contribution in Cross-Silo Federated Learning

In cross-silo federated learning, clients (e.g., organizations) collecti...

0 Chao Huang, et al. ∙