DEEPCASE: Semi-Supervised Contextual Analysis of Security Events
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Security monitoring systems detect potentially malicious activities in IT infrastructures, by either looking for known signatures or for anomalous behaviors. Security operators investigate these events to determine whether they pose a threat to their organization. In many cases, a single event may be insufficient to determine whether certain activity is indeed malicious. Therefore, a security operator frequently needs to correlate multiple events to identify if they pose a real threat. Unfortunately, the vast number of events that need to be correlated often overload security operators, forcing them to ignore some events and, thereby, potentially miss attacks. This work studies how to automatically correlate security events and, thus, automate parts of the security operator workload. We design and evaluate DEEPCASE, a system that leverages the context around events to determine which events require further inspection. This approach reduces the number of events that need to be inspected. In addition, the context provides valuable insights into why certain events are classified as malicious. We show that our approach automatically filters 86.72% of the events and reduces the manual workload of security operators by 90.53%, while underestimating the risk of potential threats in less than 0.001% of cases.
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.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
On Information and Sufficiency
Kullback, S., & Leibler, R. A. (1951) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177729694 · Cited by 20,193
Bro: a system for detecting network intruders in real-time
Paxson, V. (1999) · Computer Networks · doi:10.1016/s1389-1286(99)00112-7 · Cited by 2,636 · cited 6×
“The default method of analysing security events is provided by expert rules such as those provided by AlienVault’s OSSIM, Sigma, and the rules that can be programmed in software such as Zeek [33].”
BackgroundMethodInfluentialDeepLog: 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 11×
“Furthermore, DeepLog focuses only on anomalies, but an anomaly is not necessarily malicious.”
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×
“We also evaluate DEEPCASE on the HDFS dataset [44] used in the evaluation of the related security log”
MethodLearning Sentiment-Specific Word Embedding for Twitter Sentiment Classification
Tang, D., Wei, F., Yang, N., Zhou, M., Liu, T., & Qin, B. (2014) · Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.3115/v1/p14-1146 · Cited by 1,181 · cited 1×
“Our work embeds the input using onehot encoding, but embeddings may even be learned by the encoder itself [40].”
MethodHOLMES: Real-Time APT Detection through Correlation of Suspicious Information Flows
Milajerdi, S. M., Gjomemo, R., Eshete, B., Sekar, R., & Venkatakrishnan, V. N. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00026 · Cited by 573
UNICORN: Runtime Provenance-Based Detector for Advanced Persistent Threats
Han, X., Pasquier, T., Bates, A., Mickens, J., & Seltzer, M. (2020) · Proceedings 2020 Network and Distributed System Security Symposium · doi:10.14722/ndss.2020.24046 · Cited by 349 · cited 2×
“More automated methods such as NoDoze [22] and UNICORN [21] model the security context of systemlevel events and organization-wide events, respectively.”
BackgroundMethodFlowPrint: Semi-Supervised Mobile-App Fingerprinting on Encrypted Network Traffic
van Ede, T., Bortolameotti, R., Continella, A., Ren, J., Dubois, D. J., Lindorfer, M., Choffnes, D., van Steen, M., & Peter, A. (2020) · Proceedings 2020 Network and Distributed System Security Symposium · doi:10.14722/ndss.2020.24412 · Cited by 339 · cited 1×
“We assume that detectors include information about each host involved in an event, either by leveraging an installed agent (host-based detection), or by deriving the host from the IP address and the logs of a DHCP server (network-based detection), a common assumption in enterprise networks [17].”
BackgroundSelf-citationLiu, F., Wen, Y., Zhang, D., Jiang, X., Xing, X., & Meng, D. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3319535.3363224 · Cited by 319 · cited 1×
“2) Graph-based approaches: Other works capture context through graph-based approaches, which can be built from data [23], [30], [38].”
Background
Cited by
MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots
Deng, G., Liu, Y., Li, Y., Wang, K., Zhang, Y., Li, Z., Wang, H., Zhang, T., & Liu, Y. (2023) · arXiv · doi:10.48550/arxiv.2307.08715 · Cited by 418
“Moreover, techniques such as contextual analysis [46] could be integrated to effectively counter the encoding strategies that aim to exploit existing keyword-based defenses.”
SHADEWATCHER: Recommendation-guided Cyber Threat Analysis using System Audit Records
Zengy, J., Wang, X., Liu, J., Chen, Y., Liang, Z., Chua, T.-S., & Chua, Z. L. (2022) · 2022 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp46214.2022.9833669 · Cited by 288
MASTERKEY: Automated Jailbreaking of Large Language Model Chatbots
Deng, G., Liu, Y., Li, Y., Wang, K., Zhang, Y., Li, Z., Wang, H., Zhang, T., & Liu, Y. (2024) · Proceedings 2024 Network and Distributed System Security Symposium · doi:10.14722/ndss.2024.24188 · Cited by 137
Alert Fatigue in Security Operations Centres: Research Challenges and Opportunities
Tariq, S., Baruwal Chhetri, M., Nepal, S., & Paris, C. (2025) · ACM Computing Surveys · doi:10.1145/3723158 · Cited by 101
“Methods prioritising recall, such as anomaly detection-based intrusion detection [147] and threat intelligence integration [140], aggressively lag threats to prevent missed incidents, but this can generate excessive false positives and contribute to alert fatigue [95].”
Humans and Automation: Augmenting Security Operation Centers
Tilbury, J., & Flowerday, S. (2024) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp4030020 · Cited by 30
“Here, our results yielded two categories of solutions: the automation of the alert correlation process [49,55,56] and the automation of the triage process [43,47,48].”
BackgroundResultInfluential
Metadata
- Authors
- Ede, T. V., Aghakhani, H., Spahn, N., Bortolameotti, R., Cova, M., Continella, A., Steen, M. V., Peter, A., Kruegel, C., & Vigna, G.
- Venue
- 2022 IEEE Symposium on Security and Privacy (SP)
- Publisher
- IEEE
- Published
- 2022-05
- Pages
- 522-539
- ISSN
- 1081-6011 (ISSN-L)
- OpenAlex
- W3211484264
- Cited by
- 90
- References
- 13
- FWCI
- 19.80
- Type
- conference paper
- Language
- en
- Open access
- green
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.