From logs to Stories: Human-Centred Data Mining for Cyber Threat Intelligence
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
An average medium-sized organisation logs approx. 10 to 500 mln events per day on the system. Only less than 5% of threat alerts are being investigated by the specialised staff, leaving the security hole open for potential attacks. Insufficient information in alert message produced in machine-friendly rather than human-friendly format causes cognitive overload on currently limited cybersecurity resources. In this paper, the model that generates the report in natural language by means of applying novel storytelling techniques from security logs is proposed. The solution caters for different levels of reader expertise and preference by providing adjustable templates, filled from both local and global knowledge base. The validation is performed on case study from Security Operations Centre (SOC) at educational institution. The report generated proves superior to existing approach in terms of comprehension (increased cognition) and completeness (enriched context). The evaluation demonstrates power of storytelling in potential threats interpretation in cybersecurity context.
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
“In fact, CTI sources include information gathered from HUMman INTelligence (HUMINT), Open Source INTelligence (OSINT), TECHnical INTelligence (TECHINT) and intelligence gathered from the dark web (silk road) [232, 233].”
From Robotics cyber security: vulnerabilities, attacks, countermeasures, and recommendations (2022) · cites this paper as [232]
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
Snort - Lightweight Intrusion Detection for Networks
Roesch, M. (1999) · Cited by 3,163
Detecting 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×
“For example, a decision tree (as a level of analysis display) in the work by Xu et al. [14] was used to demonstrate how the system decides to assign a normal or abnormal label to a log record.”
MethodCarlson, M. (2015) · Digital Journalism · doi:10.1080/21670811.2014.976412 · Cited by 542
Acing the IOC Game: Toward Automatic Discovery and Analysis of Open-Source Cyber Threat Intelligence
Liao, X., Yuan, K., Wang, X., Li, Z., Xing, L., & Beyah, R. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978315 · Cited by 276 · cited 1×
“To accomplish this goal, we borrow the idea from [33] and use a scraper to monitor each website in the list of top security technical blogs to extract the associated supplementary information.”
MethodThe Role of Uncertainty, Awareness, and Trust in Visual Analytics
Sacha, D., Senaratne, H., Kwon, B. C., Ellis, G., & Keim, D. A. (2016) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2015.2467591 · Cited by 267 · cited 1×
“Visualisation presentation facilitates human cognition to improve potential issues identi-fication [13].”
BackgroundGraefe, A. (2016) · Columbia Academic Commons (Columbia University) · doi:10.7916/d80g3xdj · Cited by 186 · cited 3×
“The story can be personalised based on the needs and preferences of the individual reader [11].”
Background#FluxFlow: Visual Analysis of Anomalous Information Spreading on Social Media
Zhao, J., Cao, N., Wen, Z., Song, Y., Lin, Y.-R., & Collins, C. (2014) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2014.2346922 · Cited by 178 · cited 1×
“A significant body of literature has already sought to involve human supervision in data analysis process by visualisation techniques utilisation [12].”
BackgroundThe Incident Object Description Exchange Format
Danyliw, R., Meijer, J., & Demchenko, Y. (2007) · doi:10.17487/rfc5070 · Cited by 129
Analyzing Narratives and Story-Telling
Hyvärinen, M. (2012) · SAGE Publications Ltd eBooks · doi:10.4135/9781446212165.n26 · Cited by 112 · cited 1×
“While narrative activity is a sense-making process rather than a finished product [26], a narrative explanation can be a good candidate in analysis facilitation.”
BackgroundOne Graph Is Worth a Thousand Logs: Uncovering Hidden Structures in Massive System Event Logs
Aharon, M., Barash, G., Cohen, I., & Mordechai, E. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04180-8_32 · Cited by 70 · cited 1×
“A graph is another presentation, which was used by Aharon et al. [15] to display system behaviour status.”
MethodFLAP: An End-to-End Event Log Analysis Platform for System Management
Li, T., Jiang, Y., Zeng, C., Xia, B., Liu, Z., Zhou, W., Zhu, X., Wang, W., Zhang, L., Wu, J., et al. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098022 · Cited by 45 · cited 1×
“Li et al. in [17] proposed a system to handle various types of events logs by providing a facile way of analysing.”
BackgroundA comparative analysis of incident reporting formats
Menges, F., & Pernul, G. (2018) · Computers & Security · doi:10.1016/j.cose.2017.10.009 · Cited by 45 · cited 1×
“In cybersecurity area, information exchange formats were proposed to enhance knowledge of every single participant to address the lack of comprehensive analysis in the use of gathering all significant aspects [20].”
BackgroundCRUSOE: Data Model for Cyber Situational Awareness
Komárková, J., Husák, M., Laštovička, M., & Tovarňák, D. (2018) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3230833.3232798 · Cited by 31 · cited 1×
“They are created for various purposes [23], and machine-readable format makes it extremely challenging to understand the components and the relations between them.”
BackgroundDesigning an Algorithm-Driven Text Generation System for Personalized and Interactive News Reading
Kim, D., & Lee, J. (2018) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2018.1437864 · Cited by 29
Semantic Interpretation of Structured Log Files
Nimbalkar, P., Mulwad, V., Puranik, N., Joshi, A., & Finin, T. (2016) · IEEE International Conference on Information Reuse and Integration (IRI) · doi:10.1109/iri.2016.81 · Cited by 21 · cited 1×
“Nimbalkar et al. [19] translated log files and added semantics keywords.”
BackgroundDriving Under the Influence (of Language)
Barrett, D. P., Bronikowski, S. A., Yu, H., & Siskind, J. M. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2693278 · Cited by 20
Automated Cyber Situation Awareness Tools and Models for Improving Analyst Performance
Albanese, M., Çam, H., & Jajodia, S. (2014) · Advances in information security · doi:10.1007/978-3-319-10374-7_3 · Cited by 17
Implementation of robot journalism by programming custombot using tokenization and custom tagging
Lee, N., Kim, K., & Yoon, T. (2017) · International Conference on Advanced Communication Technology · doi:10.23919/icact.2017.7890154 · Cited by 17 · cited 1×
“Automated journalism is a recent accomplishment in story generation field [7]–[10].”
BackgroundInternet of Things Based Data Driven Storytelling for Supporting Social Connections
Wu, Q., Shen, Z., Leungy, C., Zhang, H., Ailiya, Cai, Y., & Miao, C. (2013) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/greencom-ithings-cpscom.2013.83 · Cited by 11 · cited 3×
“Wu et al. [6] proposed a data-driven storytelling system for social connections improvement.”
BackgroundInfluentialAutomatic detection of multi-line templates in software log files
Jayathilake, P. W. D. C., Weeraddana, N. R., & Hettiarachchi, H. K. E. P. (2017) · International Conference on Advances in ICT for Emerging Regions · doi:10.1109/icter.2017.8257824 · Cited by 6 · cited 1×
“As such, situational awareness system has been designed to compile, process, and fuse data from several different perspectives [4].”
BackgroundTowards Better Attack Path Visualizations Based on Deep Normalization of Host/Network IDS Alerts
Azodi, A., Cheng, F., & Meinel, C. (2016) · International Conference on Advanced Information Networking and Applications (AINA) · doi:10.1109/aina.2016.129 · Cited by 5 · cited 1×
“Azodi et al. [18] attempted to address the issue by paths of attacks identification.”
BackgroundCybersecurity Management Through Logging Analytics
Muggler, M., Eshwarappa, R., & Cankaya, E. C. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-60585-2_1 · Cited by 4 · cited 2×
“For instance, abnormal activity was recognised by the application of various machine learning techniques including Naive Bayes, K-Nearest Neighbours, and Support Vector Machines to high volumes of logs by Muggler et al. [2].”
BackgroundMethodRobot Language Learning, Generation, and ComprehensionPreprint
Barrett, D. P., Bronikowski, S. A., Yu, H., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1508.06161 · Cited by 3 · cited 1×
“Automated journalism is a recent accomplishment in story generation field [7]–[10].”
Background
Research works printed but not linked: 12
- egorov, 2002, SNORTRAN: An optimizing compiler for snort rules, Fidelis Security Systems, 1
- 2019, Data Mining for Threat Intelligence
- stevenson, 2018, Foresee Human and Machine Learning Working Together
- samii, 2019, Interactive Visualization for System Log Analysis
- jana, 2018, Crusoe: Data model for cyber situational awareness, Proc 13th Int Conf Availability Rel Secur
- gargano, 2019, Windows Defender Security Intelligence
- total, 2019, VirusTotal-Free Online Virus Malware and URL Scanner
- vink, 2010, Storytelling|Design Research Techniques
- dickson, 2017, Text Classification of Network Intrusion Alerts to Enhance Cyber Situation Awareness and Automate Alert Triage
- 2017, Structured threat information expression
- 2008, X-ARF Network Abuse Reporting 2 0
- pawlinski, 2014, Standards and tools for exchange and processing of actionable information, European Union Agency for Netw Inf Security
Cited by
Sarker, I. H. (2022) · SN Computer Science · doi:10.1007/s42979-022-01043-x · Cited by 1,208
“[1] provide human-centered data mining for cyber threat information.”
BackgroundArtificial intelligence for cybersecurity: Literature review and future research directions
Kaur, R., Gabrijelčič, D., & Klobučar, T. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101804 · Cited by 615
Robotics cyber security: vulnerabilities, attacks, countermeasures, and recommendations
Yaacoub, J.-P. A., Noura, H. N., Salman, O., & Chehab, A. (2022) · International Journal of Information Security · doi:10.1007/s10207-021-00545-8 · Cited by 320
Security Operations Center: A Systematic Study and Open Challenges
Vielberth, M., Bohm, F., Fichtinger, I., & Pernul, G. (2020) · IEEE Access · doi:10.1109/access.2020.3045514 · Cited by 214
“A fairly new approach to SOC is data presentation using storytelling presented by Afzaliseresht et al. [169].”
MethodSaeed, S., Suayyid, S. A., Al-Ghamdi, M. S., Al-Muhaisen, H., & Almuhaideb, A. M. (2023) · Sensors · doi:10.3390/s23167273 · Cited by 151
“In the context of knowledge sharing and training, Afzaliseresht et al. [36] discussed a common problem in cybersecurity in which organizations receive many machine-generated threat alerts.”
BackgroundMethodInfluential
Metadata
- Authors
- Afzaliseresht, N., Miao, Y., Michalska, S., Liu, Q., & Wang, H.
- Affiliations
- Commonwealth Scientific and Industrial Research Organisation (AU)
- Victoria University (AU)
- Venue
- IEEE Access
- Published
- 2020
- Volume
- 8
- Pages
- 19089-19099
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3000666967
- Cited by
- 47
- References
- 22
- Citations by year
- 2026: 6 · 2025: 8 · 2024: 10 · 2023: 10 · 2022: 4 · 2021: 4 · 2020: 4
- FWCI
- 5.17
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- Victoria University Research Repository (Victoria University) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Australian Government Research Training Program Scholarship
- Topics
- Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Data Visualization and Analytics
- Keywords
- cyber threat intelligence, security logs, storytelling, cognitive overload, security operations center, knowledge base
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.