End-To-End Anomaly Detection for Identifying Malicious Cyber Behavior through NLP-Based Log Embeddings
Not on the map. Why?
Abstract (arXiv)
Rule-based IDS (intrusion detection systems) are being replaced by more robust neural IDS, which demonstrate great potential in the field of Cybersecurity. However, these ML approaches continue to rely on ad-hoc feature engineering techniques, which lack the capacity to vectorize inputs in ways that are fully relevant to the discovery of anomalous cyber activity. We propose a deep end-to-end framework with NLP-inspired components for identifying potentially malicious behaviors on enterprise computer networks. We also demonstrate the efficacy of this technique on the recently released DARPA OpTC data set.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 8 of its 33 references that are in the map. First posted on arXiv 27 Aug 2021.
Builds on
8 of 33 references.
References · 8
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
- 2014DeepWalk: Online Learning of Social Representationscited by 1,547
- 2020Enhancing Robustness Against Adversarial Examples in Network Intrusion Detection Systemscited by 7
- 2021Analyzing the Usefulness of the DARPA OpTC Dataset in Cyber Threat Detection Researchcited by 7
- 2020Experimental Review of Neural-based approaches for Network Intrusion Managementcited by 5
- 2019Automated Ransomware Behavior Analysis: Pattern Extraction and Early Detectioncited by 3
- 2018Defining a Metric Space of Host Logs and Operational Use Casescited by 2
- 2021Robustness of ML-Enhanced IDS to Stealthy Adversariescited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.