Log-based anomaly detection with deep learning: how far are we?
Open accessThe DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.
Abstract
Software-intensive systems produce logs for troubleshooting purposes. Recently, many deep learning models have been proposed to automatically detect system anomalies based on log data. These models typically claim very high detection accuracy. For example, most models report an F-measure greater than 0.9 on the commonly-used HDFS dataset. To achieve a profound understanding of how far we are from solving the problem of log-based anomaly detection, in this paper, we conduct an in-depth analysis of five state-of-the-art deep learning-based models for detecting system anomalies on four public log datasets. Our experiments focus on several aspects of model evaluation, including training data selection, data grouping, class distribution, data noise, and early detection ability. Our results point out that all these aspects have significant impact on the evaluation, and that all the studied models do not always work well. The problem of log-based anomaly detection has not been solved yet. Based on our findings, we also suggest possible future work.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Extensive machine learning and deep learning-based techniques have been proposed in research for automated log anomaly detection [9], [10], with the aim of reducing manual analysis costs.”
From Practitioners’ expectations on log anomaly detection (2025) · cites this paper as [10]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“However, the adoption of LLM agents in the AIOps field, especially with noisy and lengthy data, remains limited [21,28].”
From RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models (2024) · cites this paper as [21]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“For example, Logsy [39] utilizes the Transformer network [46] to detect anomalies from log data.”
MethodExploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 1×
“PLELog extracts the semantic vectors of log templates by using a pre-trained Glovemodel [41].”
MethodLearning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · cited 1×
“Recurrent Neural Networks (RNNs), including its variants Long Short-Term Memory (LSTM) [21] and Gated Recurrent Units (GRUs) [9], are neural networks designed to handle the sequential inputs with arbitrary length.”
BackgroundConvolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831 · cited 1×
“In [33], a CNN model originally designed for sentence classification [25] is applied to log-based anomaly detection.”
MethodLearning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1406.1078 · Cited by 3,317 · cited 1×
“Recurrent Neural Networks (RNNs), including its variants Long Short-Term Memory (LSTM) [21] and Gated Recurrent Units (GRUs) [9], are neural networks designed to handle the sequential inputs with arbitrary length.”
Backgroundhdbscan: Hierarchical density based clustering
McInnes, L., Healy, J., & Astels, S. (2017) · The Journal of Open Source Software · doi:10.21105/joss.00205 · Cited by 2,833 · cited 2×
“PLELog adopts a clustering method (i.e., HDBSCAN [35]) to probabilistically estimate the labels of unlabeled log sequences.”
BackgroundBeyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation
Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006) · Lecture Notes in Computer Science · doi:10.1007/11941439_114 · Cited by 1,974 · cited 1×
“Specificity [43, 49], which is the percentage of log sequences that are correctly identified normal over all real normal sequences, can measure the probability of false alarms.”
BackgroundDeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning
Du, M., Li, F., Zheng, G., & Srikumar, V. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134015 · Cited by 1,835 · cited 10×
“To answer the above questions, we conduct a systematic evaluation of five representative deep learning models for log-based anomaly detection (including DeepLog [12], LogAnomaly [36], PLELog [48], LogRobust [54], and CNN [33]) on four datasets (including HDFS, BGL, Spirit, and Thunderbird), under controlled experiment…”
BackgroundMethodInfluentialDetecting large-scale system problems by mining console logs
Xu, W., Huang, L., Fox, A., Patterson, D., & Jordan, M. I. (2009) · Proceedings of the ACM SIGOPS 22nd symposium on Operating systems principles · doi:10.1145/1629575.1629587 · Cited by 1,332 · cited 1×
“Over the years, many data-driven methods have been proposed to automatically detect system anomalies by analyzing log data [6, 7, 12, 29, 47, 50, 54].”
Research works printed but not linked: 2
- [21] Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735-1780. -
- [31] XuLiu, Weiyou Liu, Xiaoqiang Di, Jinqing Li, Binbin Cai, Weiwu Ren, and Huamin Yang. 2021. LogNADS: Network anomaly detection scheme based on semantic representation. Future Generation Computer Systems (2021). -
Cited by
Deep learning for anomaly detection in log data: A survey
Landauer, M., Onder, S., Skopik, F., & Wurzenberger, M. (2023) · Machine Learning with Applications · doi:10.1016/j.mlwa.2023.100470 · Cited by 202
“tions of evaluation results, it is recommended to also compute metrics that are more robust against class imbalance, such as the specificity or true negative rate [10].”
BackgroundMethodInfluentialLog Parsing with Prompt-based Few-shot Learning
Le, V.-H., & Zhang, H. (2023) · 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) · doi:10.1109/icse48619.2023.00204 · Cited by 129
“Typical applications of log analysis include anomaly detection [1], [54], [55], [56], failure prediction [7], [8], root cause analysis [5], [6], etc.”
MethodSelf-citationLILAC: Log Parsing using LLMs with Adaptive Parsing Cache
Jiang, Z., Liu, J., Chen, Z., Li, Y., Huang, J., Huo, Y., He, P., Gu, J., & Lyu, M. R. (2024) · Proceedings of the ACM on Software Engineering · doi:10.1145/3643733 · Cited by 123
“LILAC consists of two main components, the ICL-enhanced parser and the adaptive parsing cache .”
LogFiT: Log Anomaly Detection Using Fine-Tuned Language Models
Almodovar, C., Sabrina, F., Karimi, S., & Azad, S. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3358730 · Cited by 111
“Consequently, Machine Learning (ML) and Deep Learning (DL)-based solutions have been proposed to automatically detect anomalies from system log data, thereby reducing the burden on human operators [4], [5], [6].”
BackgroundLogGPT: Exploring ChatGPT for Log-Based Anomaly Detection
Qi, J., Huang, S., Luan, Z., Yang, S., Fung, C., Yang, H., Qian, D., Shang, J., Xiao, Z., & Wu, Z. (2023) · 2023 IEEE International Conference on High Performance Computing & Communications, Data Science & Systems, Smart City & Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys) · doi:10.1109/hpcc-dss-smartcity-dependsys60770.2023.00045 · Cited by 102
“We believe this is still due to the abnormal diversity, BGL (143 anomaly) has more diversity of abnormal than Spirit (121 anomaly).”
MethodInfluentialRCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models
Wang, Z., Liu, Z., Zhang, Y., Zhong, A., Wang, J., Yin, F., Fan, L., Wu, L., & Wen, Q. (2024) · Proceedings of the 33rd ACM International Conference on Information and Knowledge Management · doi:10.1145/3627673.3680016 · Cited by 99
LogGPT: Log Anomaly Detection via GPT
Han, X., Yuan, S., & Trabelsi, M. (2023) · 2023 IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386543 · Cited by 63
LogEncoder: Log-Based Contrastive Representation Learning for Anomaly Detection
Qi, J., Luan, Z., Huang, S., Fung, C., Yang, H., Li, H., Zhu, D., & Qian, D. (2023) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2023.3239522 · Cited by 75
“We use chronological strategy [13] to split the training and testing set.”
BackgroundMethodLandauer, M., Skopik, F., & Wurzenberger, M. (2024) · Proceedings of the ACM on Software Engineering · doi:10.1145/3660768 · Cited by 61
“…approaches additionally apply a sliding window on the sequences (a window of size 5 with step width of 2 is displayed in the figure as an example) [23], compute event counts in sequences or windows [26], transform log messages into numeric vectors with embedding techniques [41], apply weighting…”
BackgroundMethodResultInfluentialLogGD: Detecting Anomalies from System Logs with Graph Neural Networks
Xie, Y., Zhang, H., & Babar, M. A. (2022) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs57517.2022.00039 · Cited by 96
“However, these systems are from real-world industrial systems and are widely used in the existing work [2], [20], [21], [48].”
BackgroundMethodSelf-citationInterpretable Online Log Analysis Using Large Language Models with Prompt Strategies
Liu, Y., Tao, S., Meng, W., Wang, J., Ma, W., Chen, Y., Zhao, Y., Yang, H., & Jiang, Y. (2024) · Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension · doi:10.1145/3643916.3644408 · Cited by 47
“Following the paradigm of anomaly detection raised in [17], we first parse each input log into a log template and form log sessions from templates, using fixed-window grouping with a length of 100 templates.”
BackgroundMethodLog Parsing: How Far Can ChatGPT Go?
Le, V.-H., & Zhang, H. (2023) · 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase56229.2023.00206 · Cited by 51
“They record system events and dynamic runtime information, which can help developers and operators understand system behavior and perform system diagnostic tasks, such as anomaly detection [1]–[4], failure prediction [5], [6], and failure diagnosis [7], [8].”
BackgroundSelf-citationTwin Graph-Based Anomaly Detection via Attentive Multi-Modal Learning for Microservice System
Huang, J., Yang, Y., Yu, H., Li, J., & Zheng, X. (2023) · 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase56229.2023.00138 · Cited by 50
“PLELog [7] is a semi-supervised log-based anomaly detection approach via probabilistic label estimation based on an attention-based GRU neural network.”
MethodLLMeLog: An Approach for Anomaly Detection based on LLM-enriched Log Events
He, M., Jia, T., Duan, C., Cai, H., Li, Y., & Huang, G. (2024) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre62328.2024.00023 · Cited by 79
On the effectiveness of log representation for log-based anomaly detection
Wu, X., Li, H., & Khomh, F. (2023) · Empirical Software Engineering · doi:10.1007/s10664-023-10364-1 · Cited by 53
“However, we adopt a fixed window of one hour instead of six hours following the configuration in prior work (Le and Zhang 2022).”
BackgroundMethodInfluentialKnowLog: Knowledge Enhanced Pre-trained Language Model for Log Understanding
Ma, L., Yang, W., Xu, B., Jiang, S., Fei, B., Liang, J., Zhou, M., & Xiao, Y. (2024) · Proceedings of the IEEE/ACM 46th International Conference on Software Engineering · doi:10.1145/3597503.3623304 · Cited by 35
LogShrink: Effective Log Compression by Leveraging Commonality and Variability of Log Data
Li, X., Zhang, H., Le, V.-H., & Chen, P. (2024) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3597503.3608129 · Cited by 53
Self-citationPreLog: A Pre-trained Model for Log Analytics
Le, V.-H., & Zhang, H. (2024) · Proceedings of the ACM on Management of Data · doi:10.1145/3654966 · Cited by 46
Self-citationFramework for automatic detection of anomalies in DevOps
Fawzy, A., Wassif, K. T., & Moussa, H. (2023) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2023.02.010 · Cited by 53
A Multi-Agent System for Cybersecurity Threat Detection and Correlation Using Large Language Models
Hmimou, Y., Tabaa, M., Khiat, A., & Hidila, Z. (2025) · IEEE Access · doi:10.1109/access.2025.3602681 · Cited by 25
“Le and Zhang [53] provided a comprehensive review of deep learning techniques applied to system logs, highlighting both their effectiveness and limitations in real-world environments.”
A Semisupervised Approach for Industrial Anomaly Detection via Self-Adaptive Clustering
Ma, X., Keung, J., He, P., Xiao, Y., Yu, X., & Li, Y. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3280246 · Cited by 27
DronLomaly: Runtime Detection of Anomalous Drone Behaviors via Log Analysis and Deep Learning
Shar, L. K., Minn, W., Duong, T. N. B., Fan, J., Jiang, L., & Kiat, D. L. W. (2022) · Asia-Pacific Software Engineering Conference (APSEC) · doi:10.1109/apsec57359.2022.00024 · Cited by 25
“In [21], the authors perform an extensive empirical study of several state-of-the-art deep learning models designed for anomaly detection in software systems.”
BackgroundMethodMultivariate Log-based Anomaly Detection for Distributed Database
Zhang, L., Jia, T., Jia, M., Li, Y., Yang, Y., & Wu, Z. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671725 · Cited by 47
A comprehensive study of machine learning techniques for log-based anomaly detection
Ali, S., Boufaied, C., Bianculli, D., Branco, P., & Briand, L. (2025) · Empirical Software Engineering · doi:10.1007/s10664-025-10669-3 · Cited by 50
Tele-Knowledge Pre-training for Fault Analysis
Chen, Z., Wen, Z., Huang, Y., Chen, M., Geng, Y., Yu, H., Bi, Z., Zhang, Y., Yao, Z., Song, W., et al. (2023) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde55515.2023.00265 · Cited by 44
Biglog: Unsupervised Large-scale Pre-training for a Unified Log Representation
Tao, S., Liu, Y., Meng, W., Ren, Z., Yang, H., Chen, X., Zhang, L., Xie, Y., Su, C., Oiao, X., et al. (2023) · International Workshop on Quality of Service · doi:10.1109/iwqos57198.2023.10188759 · Cited by 39
“The results are shown in Table VI. Biglog achieves strong results both in Specificity and F1-score against other baselines over different datasets, and ranks best in average scores.”
BackgroundMethodInfluentialAI for IT Operations (AIOps) on Cloud Platforms: Reviews, Opportunities and Challenges
Cheng, Q., Sahoo, D., Saha, A., Yang, W., Liu, C., Woo, G., Singh, M., Saverese, S., & Hoi, S. C. H. (2023) · arXiv · doi:10.48550/arxiv.2304.04661 · Cited by 23
“[17], [18], [19], [20], [21], [22], [23].”
Anomaly Detection on Interleaved Log Data With Semantic Association Mining on Log-Entity Graph
Chu, G., Wang, J., Qi, Q., Sun, H., Zhuang, Z., He, B., Jing, Y., Zhang, L., & Liao, J. (2025) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2025.3527856 · Cited by 28
“These datasets are also used in existing works such as [9], [12], [18], [21].”
Xiao, R., Li, W., Lu, J., & Jin, S. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3400283 · Cited by 23
“The common overall framework of most existing log-based anomaly detection methods [3], [31], [32] is depicted in Figure 2.”
MethodSurvey and Benchmark of Anomaly Detection in Business Processes
Guan, W., Cao, J., Zhao, H., Gu, Y., & Qian, S. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3484159 · Cited by 24
“[20]benchmarkfivedeeplearning-basedmethods fordetectingsystemanomaliesacrossfourpublicsystemlog datasets.”
Zhang, B., Zhang, H., Le, V.-H., Moscato, P., & Zhang, A. (2022) · Automated Software Engineering · doi:10.1007/s10515-022-00370-w · Cited by 24
“Existing semi-supervised model, although only require normal labelled data, still suffer from inaccurate detection results (Le and Zhang 2022; He et al. 2016).”
BackgroundSelf-citationSystematic Evaluation of Deep Learning Models for Log-based Failure Prediction
Hadadi, F., Dawes, J. H., Shin, D., Bianculli, D., & Briand, L. (2024) · Empirical Software Engineering · doi:10.1007/s10664-024-10501-4 · Cited by 27
LogRAG: Semi-Supervised Log-based Anomaly Detection with Retrieval-Augmented Generation
Zhang, W., Zhang, Q., Yu, E., Ren, Y., Meng, Y., Qiu, M., & Wang, J. (2024) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws62655.2024.00129 · Cited by 19
Tan, Y., Liu, J., Li, Y., & Wang, J. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3539660 · Cited by 20
Demonstration-Free: Towards More Practical Log Parsing with Large Language Models
Xiao, Y., Le, V.-H., & Zhang, H. (2024) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3691620.3694994 · Cited by 61
“The rich information included in log data enables a variety of software reliability management tasks, such as detecting system anomalies [24, 25, 60], ensuring application security [33, 38, 43], and diagnosing errors [14, 16, 28].”
Self-citationLeveraging RAG-Enhanced Large Language Model for Semi-Supervised Log Anomaly Detection
Zhang, W., Zhang, Q., Yu, E., Ren, Y., Meng, Y., Qiu, M., & Wang, J. (2024) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre62328.2024.00026 · Cited by 37
“However, this approach leads to the model seeing log data from the future during the training phase (i.e., data leakage), resulting in inflated prediction performance [44].”
Self-supervised log parsing using semantic contribution difference
Yu, S., Chen, N., Wu, Y., & Dou, W. (2023) · Journal of Systems and Software · doi:10.1016/j.jss.2023.111646 · Cited by 22
AutoLog: A Log Sequence Synthesis Framework for Anomaly Detection
Huo, Y., Li, Y., Su, Y., He, P., Xie, Z., & Lyu, M. R.-T. (2023) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase56229.2023.00133 · Cited by 30
“, D-HDFS) have fixed numbers of anomaly sequences, requiring researchers to filter out some anomaly sequences or significantly lower the number of normal sequences to increase the anomaly rate in a deterministic way [23].”
BackgroundInfluentialLogOnline: A Semi-Supervised Log-Based Anomaly Detector Aided with Online Learning Mechanism
Wang, X., Song, J., Zhang, X., Tang, J., Gao, W., & Lin, Q. (2023) · 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase56229.2023.00043 · Cited by 18
Ma, X., Zou, H., He, P., Keung, J., Li, Y., Yu, X., & Sarro, F. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3513413 · Cited by 22
“Therefore, we choose the following models:”
InfluentialPractitioners’ expectations on log anomaly detection
Ma, X., Li, Y., Keung, J., Yu, X., Zou, H., Yang, Z., Sarro, F., & Barr, E. T. (2025) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2025.3586700 · Cited by 21
“Extensive machine learning (ML) and deep learning (DL)-based techniques have been proposed in research for automated log anomaly detection [9], [10], [11], with the aim of reducing manual analysis costs.”
Log Parsing with Generalization Ability under New Log Types
Yu, S., Wu, Y., Li, Z., He, P., Chen, N., & Liu, C. (2023) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3611643.3616355 · Cited by 22
“In the real world, the system’s available logs usually do not contain all log types of the system because many system states are infrequently activated and evolving systems frequently update logging statements to bring new log types to the log parser [24].”
BackgroundLogLM: From Task-Based to Instruction-Based Automated Log Analysis
Liu, Y., Ji, Y., Tao, S., He, M., Meng, W., Zhang, S., Sun, Y., Xie, Y., Chen, B., & Yang, H. (2025) · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip66354.2025.00041 · Cited by 45
“Anomaly detection, on the other hand, focuses on identifying deviations from normal log behavior, which may signal underlying issues within the system [3].”
Demystifying and Extracting Fault-indicating Information from Logs for Failure Diagnosis
Huang, J., Jiang, Z., Liu, J., Huo, Y., Gu, J., Chen, Z., Feng, C., Dong, H., Yang, Z., & Lyu, M. R.-T. (2024) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre62328.2024.00055 · Cited by 30
Ma, L., Yang, W., Li, Y., Fei, B., Zhou, M., Li, S., Jiang, S., Xu, B., & Xiao, Y. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3749840 · Cited by 29
“Following previous anomaly detection works [47, 48, 74], we use Precision, Recall, and F1 on the anomaly class as evaluation metrics.”
InfluentialSpikeLog: Log-Based Anomaly Detection via Potential-Assisted Spiking Neuron Network
Qi, J., Luan, Z., Huang, S., Fung, C., Yang, H., & Qian, D. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3347695 · Cited by 15
Anomaly Detection in Logs Using Deep Learning
Aziz, A., & Munir, K. (2024) · IEEE Access · doi:10.1109/access.2024.3506332 · Cited by 23
SemiRALD: A semi-supervised hybrid language model for robust Anomalous Log Detection
Sun, Y., Keung, J., Yang, Z., Liu, S., & Yu, H. K. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2025.107743 · Cited by 18
Utility Analysis about Log Data Anomaly Detection Based on Federated Learning
Shin, T.-H., & Kim, S.-H. (2023) · Applied Sciences · doi:10.3390/app13074495 · Cited by 18
LogETA: Time-aware cross-system log-based anomaly detection with inter-class boundary optimization
Gong, K., Luo, S., Pan, L., Zhang, L., Zhang, Y., & Yu, H. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.03.028 · Cited by 14
Zhou, J., Ying, S., Wang, S., Zhao, D., Xiang, J., Liang, K., & Liu, P. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3548050 · Cited by 17
“Unsupervised detection methods, which do not require any labeled data, can overcome this limitation, but they may suffer from low accuracy or robustness [10].”
InfluentialWeakly-Supervised Log-Based Anomaly Detection with Inexact Labels via Multi-Instance Learning
He, M., Jia, T., Duan, C.-M., Cai, H.-Q., Li, Y., & Huang, G. (2025) · International Conference on Software Engineering · doi:10.1109/icse55347.2025.00189 · Cited by 14
“This number significantly exceeds the typical number of log entries in most log sessions [33], enabling the verification of the advantages of inexact labeling strategy in reducing annotation costs.”
InfluentialA new method for detecting beaconing attacks in IoT-based scada systems
Doğan, F., Polat, O., & Yardımcı, F. (2025) · International Journal of Information Security · doi:10.1007/s10207-025-01161-6 · Cited by 16
A Comparative Study on Large Language Models for Log Parsing
Astekin, M., Hort, M., & Moonen, L. (2024) · Proceedings of the ... ACM-IEEE International Symposium on Empirical Software Engineering and Measurement/International Symposium on Empirical Software Engineering and Measurement · doi:10.1145/3674805.3686684 · Cited by 22
End-to-End AutoML for Unsupervised Log Anomaly Detection
Zhang, S., Ji, Y., Luan, J., Nie, X., Chen, Z., Ma, M., Sun, Y., & Pei, D. (2024) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3691620.3695535 · Cited by 31
LogBase: A Large-Scale Benchmark for Semantic Log Parsing
Zhang, C., Xu, W., Liu, J., Zhang, L., Liu, G., Guan, J., Zhou, Q., & Zhou, S. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3728969 · Cited by 16
“Taking Alibaba Inc.’s cloud computing systems as an example, these systems generate about 30 to 50 GB of logs per hour [28].”
Unleashing the True Potential of Semantic-Based Log Parsing with Pre-Trained Language Models
Le, V.-H., Xiao, Y., & Zhang, H. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00174 · Cited by 22
Self-citationSemiSMAC: A semi-supervised framework for log anomaly detection with automated hyperparameter tuning
Sun, Y., Keung, J., Yang, Z., Liu, S., & Liao, Y. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2025.107869 · Cited by 13
LogEval: A comprehensive benchmark suite for LLMs in log analysis
Cui, T., Ma, S., Chen, Z., Xiao, T., Zhao, C., Tao, S., Liu, Y., Zhang, S., Lin, D., Liu, C., et al. (2025) · Empirical Software Engineering · doi:10.1007/s10664-025-10701-6 · Cited by 45
“…and Zhang 2023 ; Xiao et al. 2020; Zhu et al. 2019 ; Wang et al. 2022), log anomaly detection (Du et al. 2017 ; Meng et al. 2019 ; Guo et al. 2021; Le and Zhang 2022; Zhao et al. 2021; Zhang et al. 2019 ; Du et al. 2021), log fault diagnosis (Jia et al. 2021; Zhou et al. 2019; Zhang et al. 2021 ;…”
Speed and Performance of Parserless and Unsupervised Anomaly Detection Methods on Software Logs
Nyyssölä, J., & Mäntylä, M. (2024) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs62785.2024.00071 · Cited by 14
Learning from User-driven Events to Generate Automation Sequences
Song, Y., Bian, Y., Wang, X., & Cai, Z. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3631427 · Cited by 10
“The data is chronologically split [24] into a training set (30%, data from week 1 to 4) and a test set (70%, week 5 to 13) to simulate real-world scenarios where only historical logs are available.”
BackgroundWatch Your Callback: Offline Anomaly Detection Using Machine Learning in ROS 2
Kang, J., Kim, K. Y., & Kwon, D. (2025) · IEEE Access · doi:10.1109/access.2025.3556864 · Cited by 9
LUK: Empowering Log Understanding With Expert Knowledge From Large Language Models
Ma, L., Yang, W., Jiang, S., Fei, B., Zhou, M., Li, S., Zhao, M., Xu, B., & Xiao, Y. (2025) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2025.3594046 · Cited by 17
“In real-world scenarios, acquiring a considerable quantity of annotated samples is difficult [12], [23], thereby presenting a significant obstacle to the efficacy of automated log analysis models.”
Reducing Events to Augment Log-based Anomaly Detection Models: An Empirical Study
Zhang, L., Jia, T., Wang, K., Jia, M., Yang, Y., & Li, Y. (2024) · Proceedings of the ... ACM-IEEE International Symposium on Empirical Software Engineering and Measurement/International Symposium on Empirical Software Engineering and Measurement · doi:10.1145/3674805.3695403 · Cited by 12
Efficient Log-based Anomaly Detection with Knowledge Distillation
Nguyen, H., Nguyen, L.-V., Le, V.-H., Zhang, H., & Le, M.-T. (2024) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws62655.2024.00078 · Cited by 12
“Therefore, in this RQ, we compare the results with the chronological selection proposed in [9] (training and testing sets are separated by the time order).”
BackgroundMethodResultInfluentialSelf-citationOMLog: Online Log Anomaly Detection for Evolving System With Meta-Learning
Tian, J., Li, M., Wang, Z., Chen, L., Qin, J., & Zhang, R. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3569628 · Cited by 10
“Therefore, on the evolving dataset BGL, we additionally introduce four log parsers, Spell [29], AEL [26], Drain [23], and Brain [34], for generating different degrees of noise to more comprehensively evaluate the robustness of OMLog.”
LogBASA: Log Anomaly Detection Based on System Behavior Analysis and Global Semantic Awareness
Liao, L., Zhu, K., Luo, J., & Cai, J. (2023) · International Journal of Intelligent Systems · doi:10.1155/2023/3777826 · Cited by 10
Fuzzy CNN Autoencoder for Unsupervised Anomaly Detection in Log Data
Gorohov, O., Petrovskiy, M., Машечкин, И. В., & Kazachuk, M. (2023) · Mathematics · doi:10.3390/math11183995 · Cited by 10
Qiu, Z., Zhou, Z., Niblett, B., Johnston, A., Schwartzentruber, J., Zincir-Heywood, N., & Heywood, M. I. (2023) · International Journal of Network Management · doi:10.1002/nem.2251 · Cited by 8
“As such, we therefore aim to build on the previous benchmarking study of Le and Zhang 22 to answer how unsupervised approaches might perform under the log file anomaly detection task.”
MethodDeepUserLog: Deep Anomaly Detection on User Log Using Semantic Analysis and Key-Value Data
Wang, W., Lu, S., Luo, J., & Wu, C. (2023) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre59848.2023.00046 · Cited by 7
Domain Tailored Large Language Models for Log Mask Prediction in Cellular Network Diagnostics
Taheri, S., Ihalage, A. A., Mishra, P., Coaker, S., Faris, M., & Al-Raweshidy, H. S. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3541384 · Cited by 7
LLM Meets ML: Data-efficient Anomaly Detection on Unstable Logs
Hadadi, F., Xu, Q., Bianculli, D., & Briand, L. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3771283 · Cited by 37
“We followed the implementation of Le and Zhang [52] and truncated these long sessions to ensure that all sessions were within the 30-template limit.”
InfluentialSoftware Failure Log Analysis for Engineers—Review
Dobrowolski, W., Nikodem, M., & Unold, O. (2023) · Electronics · doi:10.3390/electronics12102260 · Cited by 12
LLM meets ML: Data-efficient Anomaly Detection on Unstable Logs
Hadadi, F., Xu, Q., Bianculli, D., & Briand, L. (2024) · arXiv · doi:10.48550/arxiv.2406.07467 · Cited by 7
“We followed the implementation of Le and Zhang [52] and truncated these long sessions to ensure that all sessions were within the 30-template limit.”
InfluentialLightweight Multi-Task Learning Method for System Log Anomaly Detection
Pham, T.-A., & Lee, J. (2024) · IEEE Access · doi:10.1109/access.2024.3425369 · Cited by 8
Multi-Parameter Log Anomaly Detection with an Unsupervised Learning Approach
Uchida, H., Tominaga, K., Itai, H., Li, Y., & Nakatoh, Y. (2024) · International Symposium on Parallel Computing and Distributed Systems (PCDS) · doi:10.1109/pcds61776.2024.10743635 · Cited by 7
“According to various survey papers, while high accuracy is reported in the field of log anomaly detection, there are also issues such as bias in the types of datasets used for evaluation and variability in accuracy due to the grouping of input data [1, 2].”
BackgroundLogContrast: Log-based Anomaly Detection Using BERT and Contrastive Learning
Yuan, W., Sun, H., Pang, M., Wang, H., Wu, G., & Zhang, Y. (2024) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom63139.2024.00349 · Cited by 9
Cross-System Software Log-based Anomaly Detection Using Meta-Learning
Wang, Y., Mäntylä, M., Nyyssölä, J., Ping, K., & Wang, L. (2025) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner64311.2025.00049 · Cited by 16
CoLA: Model Collaboration for Log-Based Anomaly Detection
Zhu, X., Xiu, T., Wu, S., Li, J., Wang, H., Yao, C., Xu, Q., & Chen, G. (2025) · Proceedings of the VLDB Endowment · doi:10.14778/3749646.3749668 · Cited by 8
“Recently, many deep learning-based small detection models (SDMs) [4, 16, 21, 39] have been proposed to automatically detect system anomalies, obviating the need for manual expert inspection.”
ADALog: Adaptive Unsupervised Anomaly detection in Logs with Self-attention Masked Language Model
Pospieszny, P., Mormul, W., Szyndler, K., & Kumar, S. (2025) · International Conference on Machine Learning Technologies (ICMLT) · doi:10.1109/icmlt65785.2025.11193311 · Cited by 14
Yicheng, S. U. N., Keung, J., Yang, Z., Liu, S., Zhang, J., & Liao, Y. (2025) · Automated Software Engineering · doi:10.1007/s10515-025-00548-y · Cited by 10
“Parsing log messages into log events, which represent the constant components of message templates, has been widely studied (Le and Zhang 2022 ).”
InfluentialXu, W., Luo, J., Huang, T., Sui, K., Geng, J., Ma, Q., Akasaka, I., Shi, X., Tang, J., & Cai, P. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00310 · Cited by 33
LogLAA: an adaptive integrated log anomaly analysis framework
Gao, Y., Luo, T., Huang, K., Tang, J., & Li, X. (2026) · Cybersecurity · doi:10.1186/s42400-026-00573-8 · Cited by 7
Log-based Anomaly Detection of Enterprise Software: An Empirical Study
Wijesinghe, N., & Hemmati, H. (2023) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs60937.2023.00012 · Cited by 8
“According to a recent study [33], the data leak during random sampling makes the effectiveness of models seem higher than they actually are.”
BackgroundResultDesign for dependability — State of the art and trends
Liu, H., Huang, C., Sun, K., Yin, J., Wu, X., Wang, J., Zhang, Q., Zheng, Y., Nigam, V., Liu, F., et al. (2024) · Journal of Systems and Software · doi:10.1016/j.jss.2024.111989 · Cited by 6
DA-Parser: A Pre-trained Domain-aware Parsing Framework for Heterogeneous Log Analysis
Tao, S., Liu, Y., Meng, W., Wang, J., Zhao, Y., Su, C., Tian, W., Zhang, M., Yang, H., & Chen, X. (2023) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac57700.2023.00050 · Cited by 8
“It has been widely discussed that the performance of log parsers may have a significant impact on the accuracy of downstream log analysis tasks [1], [13], [14].”
BackgroundBridging the Gap: LLM-Powered Transfer Learning for Log Anomaly Detection in New Software Systems
Sui, Y., Wang, X., Cui, T., Xiao, T., He, C., Zhang, S., Zhang, Y., Yang, X., Sun, Y., & Pei, D. (2025) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65448.2025.00331 · Cited by 20
“Based on previous research [47], randomly selecting samples from datasets for training can introduce unfair biases due to data leakage.”
Cheng, K., Tang, W., Tan, L., Yang, J., & Chen, J. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3605764 · Cited by 8
“Subsequently, following Le et al.’s study [46], where it was reported that a more accurate template extraction method was able to obtain better anomaly detection accuracy, we employed DivLog [17] to perform template parsing on the structured log data, with the of reducing the amount of data storage…”
Adapting Large Language Models for Parameter-Efficient Log Anomaly Detection
Lim, Y. F., Zhu, J., & Pang, G. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8298-0_26 · Cited by 13
Auto-Logging: AI-centred Logging Instrumentation
Bogatinovski, J., & Kao, O. (2023) · IEEE/ACM International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER) · doi:10.1109/icse-nier58687.2023.00023 · Cited by 11
KAD: a knowledge formalization-based anomaly detection approach for distributed systems
Wei, X., Sun, C., & Zhang, X. (2024) · Software Quality Journal · doi:10.1007/s11219-024-09670-8 · Cited by 5
“Classical statistical-based or learning-based anomaly detection techniques attempt to extract behavioral knowledge of anomalies from system logs (Le & Zhang, 2022).”
Influentialsyslrn: learning what to monitor for efficient anomaly detection
Sanvito, D., Siracusano, G., Santhanam, S., Gonzalez, R., & Bifulco, R. (2022) · Proceedings of the 2nd European Workshop on Machine Learning and Systems · doi:10.1145/3517207.3526979 · Cited by 4
“We do not report other commonly-usedmetrics, such as Precision, since they are misleading when considering highly imbalanced data, like in our case [19].”
BackgroundJiang, W., Kim, M., Cheung, C., Kim, H., Thiruvathukal, G. K., & Davis, J. C. (2025) · Empirical Software Engineering · doi:10.1007/s10664-025-10711-4 · Cited by 30
Multi-Source Log Parsing With Pre-Trained Domain Classifier
Liu, Y., Tao, S., Meng, W., Wang, J., Yang, H., & Jiang, Y. (2023) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2023.3329144 · Cited by 6
ServerRCA: Root Cause Analysis for Server Failure using Operating System Logs
Shi, J., Jiang, S., Xu, B., & Xiao, Y. (2023) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre59848.2023.00083 · Cited by 8
Graph-Based Log Anomaly Detection via Adversarial Training
He, Z., Tang, Y., Zhao, K., Liu, J., & Chen, W. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8664-4_4 · Cited by 8
LGLog: Semi-supervised Graph Representation Learning for Anomaly Detection based on System Logs
Liu, J., Tang, Y., Liu, J., Zhao, K., & Chen, W. (2023) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs60937.2023.00014 · Cited by 5
“Log data typically exhibit a severe imbalance due to the presence of rare anomalies [25].”
BackgroundMethodInfluentialTowards More Trustworthy Deep Code Models by Enabling Out-of-Distribution Detection
Yan, Y., Duong, V., Shao, H., & Poshyvanyk, D. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00177 · Cited by 4
CSCLog: A Component Subsequence Correlation-Aware Log Anomaly Detection Method
Chen, L., Song, C., Wang, X. A., Fu, D., & Zhou, W. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3585547 · Cited by 3
AI-Driven Log Analysis: Advances and Challenges
Wang, Y., Gan, W., & Yu, P. S. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401507 · Cited by 5
Metadata
- Authors
- Le, V.-H., & Zhang, H.
- Affiliations
- University of Newcastle Australia (AU)
- Venue
- Proceedings of the 44th International Conference on Software Engineering
- Publisher
- ACM
- Published
- 2022-05-21
- Pages
- 1356-1367
- ISSN
- 0270-5257 (ISSN-L)
- OpenAlex
- W4226128225
- Cited by
- 257
- References
- 51
- Citations by year
- 2026: 59 · 2025: 88 · 2024: 57 · 2023: 49 · 2022: 4
- FWCI
- 47.97
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Funders
- Australian Research Council?s Discovery Projects (DP200102940)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Keywords
- log anomaly detection, deep learning models, model evaluation, training data selection, data grouping, class distribution, noisy data, early detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.