T
Tsubasa Takahashi
Researcher at NEC
Publications - 43
Citations - 345
Tsubasa Takahashi is an academic researcher from NEC. The author has contributed to research in topics: Computer science & Differential privacy. The author has an hindex of 7, co-authored 33 publications receiving 267 citations. Previous affiliations of Tsubasa Takahashi include University of Tsukuba.
Papers
More filters
Book ChapterDOI
TURank: twitter user ranking based on user-tweet graph analysis
TL;DR: In this paper, TURank (Twitter User Rank), which is an algorithm for evaluating users' authority scores in Twitter based on link analysis, is proposed, and experimental results show that the proposed algorithm outperforms existing algorithms.
Proceedings ArticleDOI
Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks
TL;DR: It is demonstrated that the node classifier can be deceived with high-confidence by poisoning just a single node even two-hops or more far from the target, which can be used as a benchmark in future defense attempts to develop graph convolutional neural networks with having adversary robustness.
Posted Content
P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model
TL;DR: This paper proposes privacy-preserving phased generative model (P3GM), which is a differentially privateGenerative model for releasing such sensitive data and employs the two-phase learning process to make it robust against the noise, and to increase learning efficiency.
Proceedings ArticleDOI
AutoCyclone: Automatic Mining of Cyclic Online Activities with Robust Tensor Factorization
TL;DR: The proposed CycloneM model and algorithm can capture latent cyclic patterns, trends and rare events, and the algorithm outperforms the existing state-of-the-art approaches.
Patent
Information security device and information security method
Tsubasa Takahashi,翼 高橋 +1 more
TL;DR: In this article, the authors proposed an approach to ensure anonymity of a movement path and alleviate the degree of abstraction of positioning data included in location information becoming too large when the location information is being tracked in real-time.