Backdoor Attacks on Federated Meta-Learning
원문 초록
Federated learning allows multiple users to collaboratively train a shared classification model while preserving data privacy. This approach, where model updates are aggregated by a central server, was shown to be vulnerable to poisoning backdoor attacks: a malicious user can alter the shared model to arbitrarily classify specific inputs from a given class. In this paper, we analyze the effects of backdoor attacks on federated meta-learning, where users train a model that can be adapted to different sets of output classes using only a few examples. While the ability to adapt could, in principle, make federated learning frameworks more robust to backdoor attacks (when new training examples are benign), we find that even 1-shot~attacks can be very successful and persist after additional training. To address these vulnerabilities, we propose a defense mechanism inspired by matching networks, where the class of an input is predicted from the similarity of its features with a support set of labeled examples. By removing the decision logic from the model shared with the federation, success and persistence of backdoor attacks are greatly reduced.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry Detection
Intelligent Travel Activity Monitoring: Generalized Distributed Acoustic Sensing Approaches
FLsim: A Modular and Library-Agnostic Simulation Framework for Federated Learning
Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation
Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning
FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Drift
토론
이 논문과 연결된 포럼 글이 아직 없습니다.