AnnoCTR: A Dataset for Detecting and Linking Entities, Tactics, and Techniques in Cyber Threat Reports

• URL: http://arxiv.org/abs/2404.07765v1
• Date: Thu, 11 Apr 2024 14:04:36 GMT
• Title: AnnoCTR: A Dataset for Detecting and Linking Entities, Tactics, and Techniques in Cyber Threat Reports
• Authors: Lukas Lange, Marc Müller, Ghazaleh Haratinezhad Torbati, Dragan Milchevski, Patrick Grau, Subhash Pujari, Annemarie Friedrich,
• Abstract summary: 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. 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.
• Score: 3.6785107661544805
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• CTINEXUS: Leveraging Optimized LLM In-Context Learning for Constructing Cybersecurity Knowledge Graphs Under Data Scarcity [49.657358248788945]
  Textual descriptions in cyber threat intelligence (CTI) reports are rich sources of knowledge about cyber threats. Current CTI extraction methods lack flexibility and generalizability, often resulting in inaccurate and incomplete knowledge extraction. We propose CTINexus, a novel framework leveraging optimized in-context learning (ICL) of large language models.
  arXiv  Detail & Related papers  (2024-10-28T14:18:32Z)
• KGV: Integrating Large Language Models with Knowledge Graphs for Cyber Threat Intelligence Credibility Assessment [38.312774244521]
  We propose a knowledge graph-based verifier for Cyber Threat Intelligence (CTI) quality assessment framework. Our approach introduces Large Language Models (LLMs) to automatically extract OSCTI key claims to be verified. To fill the gap in the research field, we created and made public the first dataset for threat intelligence assessment from heterogeneous sources.
  arXiv  Detail & Related papers  (2024-08-15T11:32:46Z)
• AttackER: Towards Enhancing Cyber-Attack Attribution with a Named Entity Recognition Dataset [1.9573380763700712]
  We will provide the first dataset on cyber-attack attribution. Ours offers a rich set of annotations with contextual details, including some that span phrases and sentences. We conducted extensive experiments and applied NLP techniques to demonstrate the dataset's effectiveness for attack attribution.
  arXiv  Detail & Related papers  (2024-08-09T16:10:35Z)
• AttacKG+:Boosting Attack Knowledge Graph Construction with Large Language Models [17.89951919370619]
  Large Language Models (LLMs) have achieved enormous success in a broad range of tasks. Our framework consists of four consecutive modules: rewriter, identifier, and summarizer. We represent a cyber attack as a temporally unfolding event, each temporal step of which encapsulates three layers of representation.
  arXiv  Detail & Related papers  (2024-05-08T01:41:25Z)
• Exploiting Contextual Target Attributes for Target Sentiment Classification [53.30511968323911]
  Existing PTLM-based models for TSC can be categorized into two groups: 1) fine-tuning-based models that adopt PTLM as the context encoder; 2) prompting-based models that transfer the classification task to the text/word generation task. We present a new perspective of leveraging PTLM for TSC: simultaneously leveraging the merits of both language modeling and explicit target-context interactions via contextual target attributes.
  arXiv  Detail & Related papers  (2023-12-21T11:45:28Z)
• ThreatKG: An AI-Powered System for Automated Open-Source Cyber Threat Intelligence Gathering and Management [65.0114141380651]
  ThreatKG is an automated system for OSCTI gathering and management. It efficiently collects a large number of OSCTI reports from multiple sources. It uses specialized AI-based techniques to extract high-quality knowledge about various threat entities.
  arXiv  Detail & Related papers  (2022-12-20T16:13:59Z)
• EXTRACTOR: Extracting Attack Behavior from Threat Reports [6.471387545969443]
  We propose a novel approach and tool called provenanceOR that allows precise automatic extraction of concise attack behaviors from CTI reports. provenanceOR makes no strong assumptions about the text and is capable of extracting attack behaviors as graphs from unstructured text. Our evaluation results show that provenanceOR can extract concise graphs from CTI reports and can successfully be used by cyber-analytics tools in threat-hunting.
  arXiv  Detail & Related papers  (2021-04-17T18:51:00Z)
• Predicting Themes within Complex Unstructured Texts: A Case Study on Safeguarding Reports [66.39150945184683]
  We focus on the problem of automatically identifying the main themes in a safeguarding report using supervised classification approaches. Our results show the potential of deep learning models to simulate subject-expert behaviour even for complex tasks with limited labelled data.
  arXiv  Detail & Related papers  (2020-10-27T19:48:23Z)
• InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective [84.78604733927887]
  Large-scale language models such as BERT have achieved state-of-the-art performance across a wide range of NLP tasks. Recent studies show that such BERT-based models are vulnerable facing the threats of textual adversarial attacks. We propose InfoBERT, a novel learning framework for robust fine-tuning of pre-trained language models.
  arXiv  Detail & Related papers  (2020-10-05T20:49:26Z)
• Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News [57.9843300852526]
  We introduce the more realistic and challenging task of defending against machine-generated news that also includes images and captions. To identify the possible weaknesses that adversaries can exploit, we create a NeuralNews dataset composed of 4 different types of generated articles. In addition to the valuable insights gleaned from our user study experiments, we provide a relatively effective approach based on detecting visual-semantic inconsistencies.
  arXiv  Detail & Related papers  (2020-09-16T14:13:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.