paper-with-me

Papers

Client-Side Patching against Backdoor Attacks in Federated Learning

2024-12-13 · Borja Molina-Coronado

Federated learning is a versatile framework for training models in decentralized environments. However, the trust placed in clients makes federated learning vulnerable to backdoor attacks launched by malicious participants. While many defenses have been proposed, they often fail short when facing heterogeneous data distributions among participating clients. In this paper, we propose a novel defense mechanism for federated learning systems designed to mitigate backdoor attacks on the clients-side. Our approach leverages adversarial learning techniques and model patching to neutralize the impact of backdoor attacks. Through extensive experiments on the MNIST and Fashion-MNIST datasets, we demonstrate that our defense effectively reduces backdoor accuracy, outperforming existing state-of-the-art defenses, such as LFighter, FLAME, and RoseAgg, in i.i.d. and non-i.i.d. scenarios, while maintaining competitive or superior accuracy on clean data.

📄 PDF Abstract BibTeX arXiv:2412.10605

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

Patching Activation patching studies the model's computation by altering its latent representations, the token embeddings in transformer-based language models, during the inference process

Similar Papers 제목 키워드 기반

Invariant Aggregator for Defending against Federated Backdoor Attacks

2022-10-04 · Xiaoyang Wang, Dimitrios Dimitriadis, Sanmi Koyejo, Shruti Tople

Federated learning enables training high-utility models across several clients without directly sharing their private data. As a downside, the federated setting makes the model vulnerable to various adversarial attacks i…

Federated LearningModel Optimization

SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)

2025-01-11 · Phillip Rieger, Alessandro Pegoraro, Kavita Kumari, Tigist Abera 외

Split Learning (SL) is a distributed deep learning approach enabling multiple clients and a server to collaboratively train and infer on a shared deep neural network (DNN) without requiring clients to share their private…

Federated Learning

Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning

2024-10-15 · Hassan Ali, Surya Nepal, Salil S. Kanhere, Sanjay Jha

Recent works have shown that Federated Learning (FL) is vulnerable to backdoor attacks. Existing defenses cluster submitted updates from clients and select the best cluster for aggregation. However, they often rely on un…

Federated Learning

FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning

2023-09-21 · NeurIPS 2023 11

Federated learning (FL) provides a distributed training paradigm where multiple clients can jointly train a global model without sharing their local data. However, recent studies have shown that FL offers an additional s…

BaFFLe: Backdoor detection via Feedback-based Federated Learning

2020-11-04 · Sebastien Andreina, Giorgia Azzurra Marson, Helen Möllering, Ghassan Karame

Recent studies have shown that federated learning (FL) is vulnerable to poisoning attacks that inject a backdoor into the global model. These attacks are effective even when performed by a single client, and undetectable…

Federated LearningModel Poisoning