Print Email Facebook Twitter Robust backdoor attack against federated learning Title Robust backdoor attack against federated learning Author Chen, Congwen (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Verwer, S.E. (mentor) Liang, K. (mentor) Wong, J.S.S.M. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science | Cyber Security Date 2023-08-22 Abstract Current backdoor attacks against federated learning (FL) strongly rely on universal triggers or semantic patterns, which can be easily detected and filtered by certain defense mechanisms such as norm clipping, comparing parameter divergences among local updates. In this work, we propose a new stealthy and robust backdoor attack with flexible triggers against FL defenses. To achieve this, we build a generative trigger function that can learn to manipulate the benign samples with an imperceptible flexible trigger pattern and simultaneously make the trigger pattern include the most significant hidden features of the attacker-chosen label. Moreover, our trigger generator can keep learning and adapt across different rounds, allowing it to adjust to changes in the global model. By filling the distinguishable difference (the mapping between the trigger pattern and target label), we make our attack naturally stealthy. Extensive experiments on real-world datasets verify the effectiveness and stealthiness of our attack compared to prior attacks on decentralized learning framework with eight well-studied defenses. Subject Federated LearningBackdoor attackFlexible trigger attack To reference this document use: http://resolver.tudelft.nl/uuid:1d8f5279-a15d-4739-a8e0-5e7302f3fa15 Part of collection Student theses Document type master thesis Rights © 2023 Congwen Chen Files PDF thesis_Congwen_Chen.pdf 12.03 MB Close viewer /islandora/object/uuid:1d8f5279-a15d-4739-a8e0-5e7302f3fa15/datastream/OBJ/view