Y
Yuichi Ohsita
Researcher at Osaka University
Publications - 73
Citations - 554
Yuichi Ohsita is an academic researcher from Osaka University. The author has contributed to research in topics: Traffic engineering & Traffic generation model. The author has an hindex of 11, co-authored 70 publications receiving 466 citations. Previous affiliations of Yuichi Ohsita include Nippon Telegraph and Telephone.
Papers
More filters
Journal ArticleDOI
Gradually reconfiguring virtual network topologies based on estimated traffic matrices
Yuichi Ohsita,Takashi Miyamura,Shin'ichi Arakawa,Shingo Ata,Eiji Oki,Kohei Shiomoto,Masayuki Murata +6 more
TL;DR: The results show that the method can improve the accuracy of the traffic matrix estimation and achieve an adequate VNT as is the case with the reconfiguration using the actual traffic matrices.
Proceedings ArticleDOI
Detecting distributed denial-of-service attacks by analyzing TCP SYN packets statistically
TL;DR: This paper introduces a mechanism for detecting SYN flood traffic more accurately by taking into consideration the the time variation of arrival traffic, and shows that the arrival rate of normal TCP SYN packets can be modeled by a normal distribution.
Journal ArticleDOI
Anomaly Detection in Smart Home Operation From User Behaviors and Home Conditions
TL;DR: This method models user behavior as sequences of user events including operation of home IoT devices and other monitored activities, and generates multiple event sequences by removing some events and learning the frequently observed sequences.
Journal ArticleDOI
Traffic prediction for dynamic traffic engineering
Tatsuya Otoshi,Yuichi Ohsita,Masayuki Murata,Yousuke Takahashi,Keisuke Ishibashi,Kohei Shiomoto +5 more
TL;DR: Through the simulation using actual traffic traces on a backbone network of Internet2, it is shown that traffic engineering using the traffic information predicted by the proposed prediction procedure can set up routes that accommodate traffic variation for several or more hours with efficient load balancing.
Proceedings ArticleDOI
Malicious URL sequence detection using event de-noising convolutional neural network
Toshiki Shibahara,Kohei Yamanishi,Yuta Takata,Daiki Chiba,Mitsuaki Akiyama,Takeshi Yagi,Yuichi Ohsita,Masayuki Murata +7 more
TL;DR: The EDCNN is a new CNN to reduce the negative effect of benign URLs redirected from compromised websites included in malicious URL sequences and lowers the operation cost of malware infection by reducing 47% of false alerts compared with a CNN when users access compromised websites but do not obtain exploit code due to browser fingerprinting.