SentiLog

Zhang, Di; Dong, Dewen; Han, Runzhou; Zheng, Mai

doi:10.1145/3465332.3470873

Cited by 16 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Log-based anomaly detection has been applied widely to various systems, such as operating systems [9], [10], parallel file systems [26], drones [11], [18], [20], internet of things [28], and industrial control systems [29]. Among these studies, a sequence-based approach is the common modelling technique used, where the detection is observed on a collection of log events.…”

Section: A Anomaly Detection On Logs Datamentioning

confidence: 99%

“…1) Pylogsentiment [9] is the first study which employs sentiment analysis-based anomaly detection on operating system logs using GRU and GloVe embedding. 2) SentiLog [26], similar to [9], use a two-layered BiL-STM and GloVe embedding model to perform anomaly detection on parallel file system logs. 3) TransSentLog [10] is a further development of [9] and uses a two-layered transformer encoder which used two attention heads and GloVe embedding along with integrated gradients to add explainability to the trained model.…”

Section: ) Baseline From Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Severity-Oriented Multiclass Drone Flight Logs Anomaly Detection

Silalahi,

Ahmad,

Studiawan

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The availability of log data recorded by computer-based systems such as operating system and network logs, makes it possible for the stakeholder to look after the system for monitoring, evaluation, and improvement purposes. If an incident happens to the system, the log is the first and most important artefact to recover so that investigations may be performed to gather an understanding of why such incidents may have occurred. Log-based anomaly detection is one of the common approaches to uncovering incident scenarios and finding the root cause of such incidents. In the context of drone flight, incidents reported in logs include errors during take-off, flight range issues, and cancellations of actions. Existing studies employ sequence anomaly detection to check whether an event during a drone flight is anomalous. It needs several preceding events and includes deciding if the following event is legitimate or malicious. However, one single log record can have no relationship to other log events and be malicious at the same time. Thus, several studies explored point anomaly detection, where one log record is the only feature needed. Dividing the anomalies into two categories can be overwhelming as the number of logs generated by a system is large. At the same time, it can be helpful to separate critical anomalies from the less severe ones. Therefore, this study proposes DroLoVe, a severity-oriented multiclass anomaly detection approach for drone flight log data. In accordance with the dataset characteristics, where the samples from different severity levels share common features, this paper employs a multitask-based label vector representation to train deep neural network models. After an extensive experiment on several baselines, the proposed scenario outperforms other models from existing studies with promising results. The proposed label's representation improves the prediction confidence score on various encoder types with 8.6% and 1.8% from focal and cross-entropy scenarios on average, respectively.

show abstract

Section: A Anomaly Detection On Logs Datamentioning

confidence: 99%

Section: ) Baseline From Previous Workmentioning

confidence: 99%

Severity-Oriented Multiclass Drone Flight Logs Anomaly Detection

Silalahi,

Ahmad,

Studiawan

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In an effort to combine sentiment and aspect terms within a log event, [13] introduces two attention mechanisms: context attention and content attention, along with a GRU network, for sentiment classification of log events. In order to develop a generic model, SentiLog [14] extracts logging statements obtained from various source codes of parallel file systems for training purposes. Although this approach demonstrates promising results, accessing source codes to collect logging statements is not feasible in practice.…”

Section: Related Workmentioning

confidence: 99%

TransSentLog: Interpretable Anomaly Detection Using Transformer and Sentiment Analysis on Individual Log Event

Pham,

Lee

2023

IEEE Access

View full text Add to dashboard Cite

Event logs play a crucial role in monitoring the status of IT systems. These logs contain text that describes how a system operates using natural language, which can be associated with sentiment polarity. When a system is functioning correctly, event logs generally convey positive sentiment. However, if unexpected behaviors like errors or failures occur, negative sentiment can be detected. In order to identify anomalies in individual log messages without the need for log parsing, we propose TranSentLog. This method combines Transformer and sentiment analysis, leveraging the sentiment polarity of event logs. To gain a better understanding of the model predictions, we employ Integrated Gradients, an attribution method that extracts important features from the model inputs. Through extensive experimentation on public system log datasets, we demonstrate that our proposed method overcomes the limitations of existing approaches and achieves F1 scores of 99.73% on trained datasets and 94.99% on untrained datasets.INDEX TERMS Log anomaly detection, transformer, sentiment analysis, system log, integrated gradients I. INTRODUCTION

show abstract