1 code implementation • 29 May 2024 • Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai, Yuuki Yamanaka
With our approach, we can approximate the anomaly scores for normal data using the unlabeled and anomaly data.
no code implementations • 16 Feb 2024 • Yuuki Yamanaka, Tomokatsu Takahashi, Takuya Minami, Yoshiaki Nakajima
In this paper, we propose LogELECTRA, a new log anomaly detection model that analyzes a single line of log messages more deeply on the basis of self-supervised anomaly detection.
Self-Supervised Anomaly Detection Supervised Anomaly Detection
no code implementations • 1 Nov 2022 • Tomokatsu Takahashi, Masanori Yamada, Yuuki Yamanaka, Tomoya Yamashita
In addition to the output of the teacher model, ARDIR uses the internal representation of the teacher model as a label for adversarial training.