CyberLLMInstruct: A New Dataset for Analysing Safety of Fine-Tuned LLMs Using Cyber Security Data

No abstract is available for this paper.

• Publication year

  2025

• Venue

  arXiv.org

• Publication date

  Unknown publication date

• Fields of study

  Computer Science

• Identifiers
  DOI 10.48550/arXiv.2503.09334
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Ignore Me But Don't Replace Me: Utilizing Non-Linguistic Elements for Pretraining on the Cybersecurity Domain

  2024cited by this paper
• Large Language Models for Secure Code Assessment: A Multi-Language Empirical Study

  2024cited by this paper
• CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge

  2024influential reference
• Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities

  2024cited by this paper
• Cyberattacks Using ChatGPT: Exploring Malicious Content Generation Through Prompt Engineering

  2024cited by this paper
• A Comprehensive Overview of Backdoor Attacks in Large Language Models Within Communication Networks

  2023cited by this paper
• From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy

  2023cited by this paper
• Using Large Language Models for Cybersecurity Capture-The-Flag Challenges and Certification Questions

  2023cited by this paper
• SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer Security

  2023cited by this paper
• Large Language Models and Computer Security

  2023cited by this paper
• HackMentor: Fine-Tuning Large Language Models for Cybersecurity

  2023cited by this paper
• CySecBERT: A Domain-Adapted Language Model for the Cybersecurity Domain

  2022cited by this paper
• CyBERT: Cybersecurity Claim Classification by Fine-Tuning the BERT Language Model

  2021cited by this paper
• Analysis of Cybersecurity Threats in Cloud Applications Using Deep Learning Techniques

  2019cited by this paper
• Decoupled Weight Decay Regularization

  2017influential reference
• Cyber crime as a fragmented policy field in the context of the area of freedom, security and justice

  2017cited by this paper
• National Institute of Standards and Technologyにおける超伝導研究及び生活

  2001cited by this paper

• PromptGuard a structured framework for injection resilient language models

  2026cites this paper
• Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data

  2025cites this paper
• A Unified Framework for Human AI Collaboration in Security Operations Centers with Trusted Autonomy

  2025cites this paper
• Large Language Models for Synthetic Dataset Generation of Cybersecurity Indicators of Compromise

  2025cites this paper
• Proactively Detecting Threats: A Novel Approach Using LLMs

  2025cites this paper
• EAGER: Edge-Aligned LLM Defense for Robust, Efficient, and Accurate Cybersecurity Question Answering

  2025cites this paper
• AQUA-LLM: Evaluating Accuracy, Quantization, and Adversarial Robustness Trade-offs in LLMs for Cybersecurity Question Answering

  2025cites this paper