@inproceedings{lange-etal-2024-annoctr-dataset,
title = "{A}nno{CTR}: A Dataset for Detecting and Linking Entities, Tactics, and Techniques in Cyber Threat Reports",
author = {Lange, Lukas and
M{\"u}ller, Marc and
Haratinezhad Torbati, Ghazaleh and
Milchevski, Dragan and
Grau, Patrick and
Pujari, Subhash Chandra and
Friedrich, Annemarie},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.103",
pages = "1147--1160",
abstract = "Monitoring the threat landscape to be aware of actual or potential attacks is of utmost importance to cybersecurity professionals. Information about cyber threats is typically distributed using natural language reports. Natural language processing can help with managing this large amount of unstructured information, yet to date, the topic has received little attention. With this paper, we present AnnoCTR, a new CC-BY-SA-licensed dataset of cyber threat reports. The reports have been annotated by a domain expert with named entities, temporal expressions, and cybersecurity-specific concepts including implicitly mentioned techniques and tactics. Entities and concepts are linked to Wikipedia and the MITRE ATT{\&}CK knowledge base, the most widely-used taxonomy for classifying types of attacks. Prior datasets linking to MITRE ATT{\&}CK either provide a single label per document or annotate sentences out-of-context; our dataset annotates entire documents in a much finer-grained way. In an experimental study, we model the annotations of our dataset using state-of-the-art neural models. In our few-shot scenario, we find that for identifying the MITRE ATT{\&}CK concepts that are mentioned explicitly or implicitly in a text, concept descriptions from MITRE ATT{\&}CK are an effective source for training data augmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lange-etal-2024-annoctr-dataset">
<titleInfo>
<title>AnnoCTR: A Dataset for Detecting and Linking Entities, Tactics, and Techniques in Cyber Threat Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lukas</namePart>
<namePart type="family">Lange</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Müller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ghazaleh</namePart>
<namePart type="family">Haratinezhad Torbati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dragan</namePart>
<namePart type="family">Milchevski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Grau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subhash</namePart>
<namePart type="given">Chandra</namePart>
<namePart type="family">Pujari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Monitoring the threat landscape to be aware of actual or potential attacks is of utmost importance to cybersecurity professionals. Information about cyber threats is typically distributed using natural language reports. Natural language processing can help with managing this large amount of unstructured information, yet to date, the topic has received little attention. With this paper, we present AnnoCTR, a new CC-BY-SA-licensed dataset of cyber threat reports. The reports have been annotated by a domain expert with named entities, temporal expressions, and cybersecurity-specific concepts including implicitly mentioned techniques and tactics. Entities and concepts are linked to Wikipedia and the MITRE ATT&CK knowledge base, the most widely-used taxonomy for classifying types of attacks. Prior datasets linking to MITRE ATT&CK either provide a single label per document or annotate sentences out-of-context; our dataset annotates entire documents in a much finer-grained way. In an experimental study, we model the annotations of our dataset using state-of-the-art neural models. In our few-shot scenario, we find that for identifying the MITRE ATT&CK concepts that are mentioned explicitly or implicitly in a text, concept descriptions from MITRE ATT&CK are an effective source for training data augmentation.</abstract>
<identifier type="citekey">lange-etal-2024-annoctr-dataset</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.103</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1147</start>
<end>1160</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AnnoCTR: A Dataset for Detecting and Linking Entities, Tactics, and Techniques in Cyber Threat Reports
%A Lange, Lukas
%A Müller, Marc
%A Haratinezhad Torbati, Ghazaleh
%A Milchevski, Dragan
%A Grau, Patrick
%A Pujari, Subhash Chandra
%A Friedrich, Annemarie
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F lange-etal-2024-annoctr-dataset
%X Monitoring the threat landscape to be aware of actual or potential attacks is of utmost importance to cybersecurity professionals. Information about cyber threats is typically distributed using natural language reports. Natural language processing can help with managing this large amount of unstructured information, yet to date, the topic has received little attention. With this paper, we present AnnoCTR, a new CC-BY-SA-licensed dataset of cyber threat reports. The reports have been annotated by a domain expert with named entities, temporal expressions, and cybersecurity-specific concepts including implicitly mentioned techniques and tactics. Entities and concepts are linked to Wikipedia and the MITRE ATT&CK knowledge base, the most widely-used taxonomy for classifying types of attacks. Prior datasets linking to MITRE ATT&CK either provide a single label per document or annotate sentences out-of-context; our dataset annotates entire documents in a much finer-grained way. In an experimental study, we model the annotations of our dataset using state-of-the-art neural models. In our few-shot scenario, we find that for identifying the MITRE ATT&CK concepts that are mentioned explicitly or implicitly in a text, concept descriptions from MITRE ATT&CK are an effective source for training data augmentation.
%U https://aclanthology.org/2024.lrec-main.103
%P 1147-1160
Markdown (Informal)
[AnnoCTR: A Dataset for Detecting and Linking Entities, Tactics, and Techniques in Cyber Threat Reports](https://aclanthology.org/2024.lrec-main.103) (Lange et al., LREC-COLING 2024)
ACL
- Lukas Lange, Marc Müller, Ghazaleh Haratinezhad Torbati, Dragan Milchevski, Patrick Grau, Subhash Chandra Pujari, and Annemarie Friedrich. 2024. AnnoCTR: A Dataset for Detecting and Linking Entities, Tactics, and Techniques in Cyber Threat Reports. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1147–1160, Torino, Italia. ELRA and ICCL.