Amulog project

english / japanese

In amulog project, we have constructed a platform for analyzing log data of large-scale systems such as networks.

Research topics and performance (2022 ver)

Supervised log template generation

  1. Thieu Nguyen, Satoru Kobayashi, Kensuke Fukuda, “LogDTL: Network Log Template Generation with Deep Transfer Learning”, In proceesings of the 6th IEEE/IFIP International Workshop on Analytics for Network and Service Management (AnNet 2021), pp.848-853, Virtual, May, 2021 (IFIP, IEEE, paper, slide)

  2. Satoru Kobayashi, Kensuke Fukuda, Hiroshi Esaki, “Towards an NLP-based Log Template Generation Algorithm for System Log Analysis”, In proceedings of the Ninth International Conference on Future Internet Technologies (CFI’14), p.4, Tokyo, Japan, June, 2014 (10.1145/2619287.2619290, paper)

Log template generation framework for diverse algorithms

  1. Satoru Kobayashi, Yuya Yamashiro, Kazuki Otomo, Kensuke Fukuda, “amulog: A General Log Analysis Framework for Comparison and Combination of Diverse Template Generation Methods”, International Journal of Network Management, vol.32, no.4, Wiley, Dec, 2021 (10.1002/nem.2195, submit_version)

  2. Satoru Kobayashi, Yuya Yamashiro, Kazuki Otomo, Kensuke Fukuda, “amulog: A General Log Analysis Framework for Diverse Template Generation Methods”, In proceedings of the 16th IFIP/IEEE International Conference on Network and Service Management (CNSM’20), pp.1-5, Virtual, November, 2020 (10.23919/CNSM50824.2020.9269049, IFIP, paper, poster, slide)

Semantic analysis of network operational data

  1. Kazuki Otomo, Satoru Kobayashi, Kensuke Fukuda, Osamu Akashi, Kimihiro Mizutani, Hiroshi Esaki, “Towards Extracting Semantics of Network Config Blocks”, In proceedings of the 9th IEEE International Workshop on Architecture, Design, Deployment & Management of Networks & Applications (ADMNET 2021), pp.1444-1449, Virtual, July, 2021 (10.1109/COMPSAC51774.2021.00214, paper)

  2. Kazuki Otomo, Satoru Kobayashi, Kensuke Fukuda, Hiroshi Esaki, “Latent Semantics Approach for Network Log Analysis: Modeling and its application”, In proceedings of the 17th IFIP/IEEE International Symposium on Integrated Network Management (IM’21), pp.215-223, Virtual, May, 2021 (IFIP, IEEE, paper)

Anomaly detection of log time-series

  1. Kazuki Otomo, Satoru Kobayashi, Kensuke Fukuda, Hiroshi Esaki, “Latent Variable based Anomaly Detection in Network System Logs”, IEICE Transactions on Information and Systems, pp.1644-1652, Vol.E102-D, No.9, September, 2019 (10.1587/transinf.2018OFP0007, paper)

  2. Kazuki Otomo, Satoru Kobayashi, Kensuke Fukuda, Hiroshi Esaki, “Finding Anomalies in Network System Logs with Latent Variables”, Workshop on Big Data Analytics and Machine Learning for Data Communication Networks (Big-DAMA), ACM SIGCOMM, pp.8-14, Budapest, Hungary, August, 2018 (10.1145/3229607.3229608, paper)

  3. Kazuki Otomo, Satoru Kobayashi, Kensuke Fukuda, Hiroshi Esaki, “An Analysis of Burstiness and Causality of System Logs”, Asian Internet Engineering Conference (AINTEC’17), pp.16-23, Bangkok, Thailand, November, 2017 (10.1145/3154970.3154973, paper)

Causal analysis of log time-series

  1. Satoru Kobayashi, Keiichi Shima, Kenjiro Cho, Osamu Akashi, Kensuke Fukuda, “Comparative Causal Analysis of Network Log Data in Two Large ISPs”, In proceedings of the 7th IEEE/IFIP International Workshop on Analytics for Network and Service Management (AnNet 2022), Budapest, Hungary, April, 2022 (10.1109/NOMS54207.2022.9789823, paper, slide)

  2. Richard Jarry, Satoru Kobayashi, Kensuke Fukuda, “A Quantitative Causal Analysis for Network Log Data”, In proceedings of the 9th IEEE International Workshop on Architecture, Design, Deployment & Management of Networks & Applications (ADMNET 2021), pp.1438-1443, Virtual, July, 2021 (10.1109/COMPSAC51774.2021.00213, paper, slide)

  3. Satoru Kobayashi, Kazuki Otomo, Kensuke Fukuda, “Causal analysis of network logs with layered protocols and topology knowledge”, In proceedings of the 15th IFIP/IEEE International Conference on Network and Service Management (CNSM’19), pp.1-9, Halifax, Canada, October, 2019 (10.23919/CNSM46954.2019.9012718, IFIP, paper, slide)

  4. Satoru Kobayashi, Kazuki Otomo, Kensuke Fukuda, Hiroshi Esaki, “Mining Causality of Network Events in Log Data”, IEEE Transactions on Network and Service Management, pp.53-67, vol.15, no.1, March, 2018 (10.1109/TNSM.2017.2778096, paper)

  5. Satoru Kobayashi, Kensuke Fukuda and Hiroshi Esaki, “Mining causes of network events in log data with causal inference”, In proceedings of the 13th IFIP/IEEE International Symposium on Integrated Network Management (IM’17), pp.45-53, Lisbon, Portugal, May, 2017 (10.23919/INM.2017.7987263, IFIP paper, slide)