Výsledky vyhledávání

Report

Privacy-Preserving Federated Unlearning with Certified Client Removal

Autor: Liu, Ziyao, Ye, Huanyi, Jiang, Yu, Shen, Jiyuan, Guo, Jiale, Tjuawinata, Ivan, Lam, Kwok-Yan

In recent years, Federated Unlearning (FU) has gained attention for addressing the removal of a client's influence from the global model in Federated Learning (FL) systems, thereby ensuring the ``right to be forgotten" (RTBF). State-of-the-art method

Externí odkaz: http://arxiv.org/abs/2404.09724

Zobrazit plný text záznamu

Report

General One-loop Generating Function by IBP relations

Autor: Feng, Bo, Hu, Chang, Shen, Jiyuan, Zhang, Yaobo

In this paper we have studied the most general generating function of reduction for one loop integrals with arbitrary tensor structure in numerator and arbitrary power distribution of propagators in denominator. Using IBP relations, we have establish

Externí odkaz: http://arxiv.org/abs/2403.16040

Zobrazit plný text záznamu

Report

Effective Intrusion Detection in Heterogeneous Internet-of-Things Networks via Ensemble Knowledge Distillation-based Federated Learning

Autor: Shen, Jiyuan, Yang, Wenzhuo, Chu, Zhaowei, Fan, Jiani, Niyato, Dusit, Lam, Kwok-Yan

With the rapid development of low-cost consumer electronics and cloud computing, Internet-of-Things (IoT) devices are widely adopted for supporting next-generation distributed systems such as smart cities and industrial control systems. IoT devices a

Externí odkaz: http://arxiv.org/abs/2401.11968

Zobrazit plný text záznamu

Report

Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning

Autor: Jiang, Yu, Shen, Jiyuan, Liu, Ziyao, Tan, Chee Wei, Lam, Kwok-Yan

Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients manipulate their updates to affect the global model. Although various methods exist for detecting those clients in FL, identifying malicious clients requires sufficie

Externí odkaz: http://arxiv.org/abs/2401.08216

Zobrazit plný text záznamu

Report

A Survey on Federated Unlearning: Challenges, Methods, and Future Directions

Autor: Liu, Ziyao, Jiang, Yu, Shen, Jiyuan, Peng, Minyi, Lam, Kwok-Yan, Yuan, Xingliang, Liu, Xiaoning

In recent years, the notion of ``the right to be forgotten" (RTBF) has become a crucial aspect of data privacy for digital trust and AI safety, requiring the provision of mechanisms that support the removal of personal data of individuals upon their

Externí odkaz: http://arxiv.org/abs/2310.20448

Zobrazit plný text záznamu

Report

Efficient Dataset Distillation through Alignment with Smooth and High-Quality Expert Trajectories

Autor: Shen, Jiyuan, Yang, Wenzhuo, Lam, Kwok-Yan

Training a large and state-of-the-art machine learning model typically necessitates the use of large-scale datasets, which, in turn, makes the training and parameter-tuning process expensive and time-consuming. Some researchers opt to distil informat

Externí odkaz: http://arxiv.org/abs/2310.10541

Zobrazit plný text záznamu

Report

An Explicit Expression of Generating Function for One-Loop Tensor Reduction

Autor: Hu, Chang, Li, Tingfei, Shen, Jiyuan, Xu, Yongqun

This work introduces an explicit expression for the generation function for the reduction of an $n$-gon to an $(n-k)$-gon. A novel recursive relation of generation function is formulated based on Feynman Parametrization in projective space, involving

Externí odkaz: http://arxiv.org/abs/2308.13336

Zobrazit plný text záznamu