Zobrazeno 1 - 10
of 312
pro vyhledávání: '"Sun Caijun"'
Federated learning can train models without directly providing local data to the server. However, the frequent updating of the local model brings the problem of large communication overhead. Recently, scholars have achieved the communication efficien
Externí odkaz:
http://arxiv.org/abs/2405.03248
Autor:
Yu, Guangsheng, Wang, Qin, Sun, Caijun, Nguyen, Lam Duc, Bandara, H. M. N. Dilum, Chen, Shiping
In this paper, we study how to optimize existing Non-Fungible Token (NFT) incentives. Upon exploring a large number of NFT-related standards and real-world projects, we come across an unexpected finding. That is, the current NFT incentive mechanisms,
Externí odkaz:
http://arxiv.org/abs/2402.06459
Autor:
Zhang, Zixu, Yu, Guangsheng, Sun, Caijun, Wang, Xu, Wang, Ying, Zhang, Ming, Ni, Wei, Liu, Ren Ping, Reeves, Andrew, Georgalas, Nektarios
Integrating sharded blockchain with IoT presents a solution for trust issues and optimized data flow. Sharding boosts blockchain scalability by dividing its nodes into parallel shards, yet it's vulnerable to the $1\%$ attacks where dishonest nodes ta
Externí odkaz:
http://arxiv.org/abs/2401.00632
Autor:
Yu, Guangsheng, Jiang, Yanna, Wang, Qin, Wang, Xu, Ma, Baihe, Sun, Caijun, Ni, Wei, Liu, Ren Ping
We for the first time propose, implement, and evaluate a practical Split Unlearning framework by enabling SISA-based machine unlearning (SP'21) in Split Learning (SL). We introduce SplitWiper and SplitWiper+, which leverage the inherent "Sharded" str
Externí odkaz:
http://arxiv.org/abs/2308.10422
As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. In this paper, we consider the long-tailed distribution with the presen
Externí odkaz:
http://arxiv.org/abs/2307.08324
Autor:
Ma, Baihe, Wang, Xu, Lin, Xiaojie, Jiang, Yanna, Sun, Caijun, Wang, Zhe, Yu, Guangsheng, He, Ying, Ni, Wei, Liu, Ren Ping
Location privacy is critical in vehicular networks, where drivers' trajectories and personal information can be exposed, allowing adversaries to launch data and physical attacks that threaten drivers' safety and personal security. This survey reviews
Externí odkaz:
http://arxiv.org/abs/2305.04503
Autor:
Yu, Guangsheng, Wang, Xu, Sun, Caijun, Wang, Qin, Yu, Ping, Ni, Wei, Liu, Ren Ping, Xu, Xiwei
Federated learning (FL) provides an effective machine learning (ML) architecture to protect data privacy in a distributed manner. However, the inevitable network asynchrony, the over-dependence on a central coordinator, and the lack of an open and fa
Externí odkaz:
http://arxiv.org/abs/2301.04006
Autor:
Wang, Qin, Yu, Guangsheng, Sai, Yilin, Sun, Caijun, Nguyen, Lam Duc, Xu, Sherry, Chen, Shiping
Decentralized Autonomous Organization (DAO) is an organization constructed by automatically executed rules such as via smart contracts, holding features of the permissionless committee, transparent proposals, and fair contribution by stakeholders. As
Externí odkaz:
http://arxiv.org/abs/2211.15993
Obfuscating a dataset by adding random noises to protect the privacy of sensitive samples in the training dataset is crucial to prevent data leakage to untrusted parties for edge applications. We conduct comprehensive experiments to investigate how t
Externí odkaz:
http://arxiv.org/abs/2208.03909
Publikováno v:
In Neurocomputing 1 November 2024 604
