Výsledky vyhledávání - "Privacy and Security in Machine Learning"

Beyond model splitting: Preventing label inference attacks in vertical federated learning with dispersed training Autor Wang, Yilei, Lv, Qingzhe, Zhang, Huang, Zhao, Minghao, Sun, Yuhong, Ran, Lingkai, Li, Tao

“…Federated learning is an emerging paradigm that enables multiple organizations to jointly train a model without revealing their private data. As an important…”
Získat plný text

DFedSN: Decentralized federated learning based on heterogeneous data in social networks Autor Chen, Yikuan, Liang, Li, Gao, Wei

“…Users talk with each other and share their lives online, which forms a huge social network. However, a series of potential problems such as privacy security…”
Získat plný text

Multi-stage dynamic disinformation detection with graph entropy guidance Autor Hao, Xiaorong, Liu, Bo, Yang, Xinyan, Sun, Xiangguo, Meng, Qing, Cao, Jiuxin

“…Online disinformation has become one of the most severe concerns in today’s world. Recognizing disinformation timely and effectively is very hard, because the…”
Získat plný text

GANAD: A GAN-based method for network anomaly detection Autor Fu, Jie, Wang, Lina, Ke, Jianpeng, Yang, Kang, Yu, Rongwei

“…Cyber-intrusion always leads to severe threats to the network, i,e., system paralysis, information leaky, and economic losses. To protect network security,…”
Získat plný text

NAH: neighbor-aware attention-based heterogeneous relation network model in E-commerce recommendation Autor Jiang, Nan, Hu, Zihao, Wen, Jie, Zhao, Jiahui, Gu, Weihao, Tu, Ziang, Liu, Ximeng, Li, Yuanyuan, Gong, Jianfei, Lin, Fengtao

“…Traditional recommender systems only utilize a single user-item interaction behavior as the optimization target behavior. However, multi-behavior recommender…”
Získat plný text

Efficient approximation and privacy preservation algorithms for real time online evolving data streams Autor Patil, Rahul A., Patil, Pramod D.

“…Because of the processing of continuous unstructured large streams of data, mining real-time streaming data is a more challenging research issue than mining…”
Získat plný text

Explanation-based data-free model extraction attacks Autor Yan, Anli, Hou, Ruitao, Yan, Hongyang, Liu, Xiaozhang

“…Deep learning (DL) has dramatically pushed the previous limits of various tasks, ranging from computer vision to natural language processing. Despite its…”
Získat plný text

A stealthy and robust backdoor attack via frequency domain transform Autor Hou, Ruitao, Huang, Teng, Yan, Hongyang, Ke, Lishan, Tang, Weixuan

“…Deep learning models are vulnerable to backdoor attacks, where an adversary aims to inject a hidden backdoor into the deep learning models, such that the…”
Získat plný text

On-chain repairing for multi-party data migration Autor Jiang, Wenchao, Dai, Weiqi, Lv, Qiwen, Ning, Dongjun, Lin, Sui

“…Blockchain can be used to solve the problem of mutual trust between different institutions. However, when migrating data from a traditional system to a…”
Získat plný text

TFPA: A traceable federated privacy aggregation protocol Autor Li, Xingyu, Long, Yucheng, Hu, Li, Tan, Xin, Li, Jin

“…Federated learning is gaining significant interests as it enables model training over a large volume of data that is distributedly stored over many users…”
Získat plný text