paper-with-me

홈 › Papers

Defending the Edge: Representative-Attention for Mitigating Backdoor Attacks in Federated Learning

2025-05-15 · Chibueze Peace Obioma, Youcheng Sun, Mustafa A. Mustafa

Federated learning (FL) enhances privacy and reduces communication cost for resource-constrained edge clients by supporting distributed model training at the edge. However, the heterogeneous nature of such devices produces diverse, non-independent, and identically distributed (non-IID) data, making the detection of backdoor attacks more challenging. In this paper, we propose a novel federated representative-attention-based defense mechanism, named FeRA, that leverages cross-client attention over internal feature representations to distinguish benign from malicious clients. FeRA computes an anomaly score based on representation reconstruction errors, effectively identifying clients whose internal activations significantly deviate from the group consensus. Our evaluation demonstrates FeRA's robustness across various FL scenarios, including challenging non-IID data distributions typical of edge devices. Experimental results show that it effectively reduces backdoor attack success rates while maintaining high accuracy on the main task. The method is model-agnostic, attack-agnostic, and does not require labeled reference data, making it well suited to heterogeneous and resource-limited edge deployments.

📄 PDF Abstract BibTeX arXiv:2505.10297

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor AttackFederated 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

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment

2024-11-23 · CVPR 2024 1 · Alvi Md Ishmam, Christopher Thomas

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vuln…

Language ModelingLanguage Modelling

NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning

2023-03-03 · Shengfang Zhai, Qingni Shen, Xiaoyi Chen, Weilong Wang 외

At present, backdoor attacks attract attention as they do great harm to deep learning models. The adversary poisons the training data making the model being injected with a backdoor after being trained unconsciously by v…

backdoor defenseContrastive Learning

Defending Backdoor Attacks on Vision Transformer via Patch Processing

2022-06-24 · Khoa D. Doan, Yingjie Lao, Peng Yang, Ping Li

Vision Transformers (ViTs) have a radically different architecture with significantly less inductive bias than Convolutional Neural Networks. Along with the improvement in performance, security and robustness of ViTs are…

Backdoor AttackInductive Bias

T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models

2024-07-05 · Zhongqi Wang, Jie Zhang, Shiguang Shan, Xilin Chen

While text-to-image diffusion models demonstrate impressive generation capabilities, they also exhibit vulnerability to backdoor attacks, which involve the manipulation of model outputs through malicious triggers. In thi…

Backdoor Attack

A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning

2025-08-14 · Keke Gai, Dongjue Wang, Jing Yu, Liehuang Zhu 외 arxiv

Defending backdoor attacks in Federated Learning (FL) under heterogeneous client data distributions encounters limitations balancing effectiveness and privacy-preserving, while most existing methods highly rely on the as…

Federated LearningZero-Shot Learning