paper-with-me

Papers

FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clients

2025-05-17 · Jianyi Zhang, Ziyin Zhou, Yilong Li, Qichao Jin

Federated learning (FL) is gaining increasing attention as an emerging collaborative machine learning approach, particularly in the context of large-scale computing and data systems. However, the fundamental algorithm of FL, Federated Averaging (FedAvg), is susceptible to backdoor attacks. Although researchers have proposed numerous defense algorithms, two significant challenges remain. The attack is becoming more stealthy and harder to detect, and current defense methods are unable to handle 50\% or more malicious users or assume an auxiliary server dataset. To address these challenges, we propose a novel defense algorithm, FL-PLAS, \textbf{F}ederated \textbf{L}earning based on \textbf{P}artial\textbf{ L}ayer \textbf{A}ggregation \textbf{S}trategy. In particular, we divide the local model into a feature extractor and a classifier. In each iteration, the clients only upload the parameters of a feature extractor after local training. The server then aggregates these local parameters and returns the results to the clients. Each client retains its own classifier layer, ensuring that the backdoor labels do not impact other clients. We assess the effectiveness of FL-PLAS against state-of-the-art (SOTA) backdoor attacks on three image datasets and compare our approach to six defense strategies. The results of the experiment demonstrate that our methods can effectively protect local models from backdoor attacks. Without requiring any auxiliary dataset for the server, our method achieves a high main-task accuracy with a lower backdoor accuracy even under the condition of 90\% malicious users with the attacks of trigger, semantic and edge-case.

📄 PDF Abstract BibTeX arXiv:2505.12019

Code (1)

besticsp/fl-plas 공식 구현 pytorch

Tasks

backdoor defenseFederated Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

SAFELearning: Enable Backdoor Detectability In Federated Learning With Secure Aggregation

2021-02-04 · Zhuosheng Zhang, Jiarui Li, Shucheng Yu, Christian Makaya

For model privacy, local model parameters in federated learning shall be obfuscated before sent to the remote aggregator. This technique is referred to as \emph{secure aggregation}. However, secure aggregation makes mode…

Anomaly DetectionFederated LearningModel Poisoning

Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation

2022-10-13 · Zhiyuan Zhang, Qi Su, Xu sun

Despite the potential of federated learning, it is known to be vulnerable to backdoor attacks. Many robust federated aggregation methods are proposed to reduce the potential backdoor risk. However, they are mainly valida…

Federated Learning

Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense

2023-09-21 · NeurIPS 2023 11

Federated learning algorithms enable neural network models to be trained across multiple decentralized edge devices without sharing private data. However, they are susceptible to backdoor attacks launched by malicious cl…

Robust Federated Learning with Attack-Adaptive Aggregation

2021-02-10 · Ching Pui Wan, Qifeng Chen

Federated learning is vulnerable to various attacks, such as model poisoning and backdoor attacks, even if some existing defense strategies are used. To address this challenge, we propose an attack-adaptive aggregation s…

Federated LearningModel Poisoning

Meta Federated Learning

2021-02-10 · Omid Aramoon, Pin-Yu Chen, Gang Qu, Yuan Tian

Due to its distributed methodology alongside its privacy-preserving features, Federated Learning (FL) is vulnerable to training time adversarial attacks. In this study, our focus is on backdoor attacks in which the adver…

Federated LearningPrivacy Preserving