Výsledky vyhledávání

Report

Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning

Autor: Kim, Taejin, Li, Jiarui, Singh, Shubhranshu, Madaan, Nikhil, Joe-Wong, Carlee

In today's data-driven landscape, the delicate equilibrium between safeguarding user privacy and unleashing data potential stands as a paramount concern. Federated learning, which enables collaborative model training without necessitating data sharin

Externí odkaz: http://arxiv.org/abs/2310.11594

Zobrazit plný text záznamu

Report

Characterizing Internal Evasion Attacks in Federated Learning

Autor: Kim, Taejin, Singh, Shubhranshu, Madaan, Nikhil, Joe-Wong, Carlee

Federated learning allows for clients in a distributed system to jointly train a machine learning model. However, clients' models are vulnerable to attacks during the training and testing phases. In this paper, we address the issue of adversarial cli

Externí odkaz: http://arxiv.org/abs/2209.08412

Zobrazit plný text záznamu