mlsanityData to 14 Oct 2026

Securing Educational LLMs: A Generalised Taxonomy of Attacks on LLMs and DREAD Risk Assessment

arXiv 2508.08629 ↗First posted 12 Aug 2025cs.CY cs.AIcited by 2

On the map: LLM safety and security → Prompt injection and agent security

Abstract (arXiv)

Due to perceptions of efficiency and significant productivity gains, various organisations, including in education, are adopting Large Language Models (LLMs) into their workflows. Educator-facing, learner-facing, and institution-facing LLMs, collectively, Educational Large Language Models (eLLMs), complement and enhance the effectiveness of teaching, learning, and academic operations. However, their integration into an educational setting raises significant cybersecurity concerns. A comprehensive landscape of contemporary attacks on LLMs and their impact on the educational environment is missing. This study presents a generalised taxonomy of fifty attacks on LLMs, which are categorized as attacks targeting either models or their infrastructure. The severity of these attacks is evaluated in the educational sector using the DREAD risk assessment framework. Our risk assessment indicates that token smuggling, adversarial prompts, direct injection, and multi-step jailbreak are critical attacks on eLLMs. The proposed taxonomy, its application in the educational environment, and our risk assessment will help academic and industrial practitioners to build resilient solutions that protect learners and institutions.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security. Builds on 68 of its 121 references that are in the map. First posted on arXiv 12 Aug 2025.

Builds on

68 of 121 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents27 Feb
  2. 2024Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks12 Sep
  3. 2024Threat Modelling and Risk Analysis for Large Language Model (LLM)-Powered Applications16 Jun
  4. 2023Hijacking Large Language Models via Adversarial In-Context Learning16 Nov
  5. 2023From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy3 Jul
  6. 2023Prompt Injection attack against LLM-integrated Applications8 Jun
  7. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPT11 Apr
  8. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection23 Feb

Other references · 60

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2023A Survey of Large Language Modelscited by 2,576
  3. 2020Extracting Training Data from Large Language Modelscited by 2,189
  4. 2023BloombergGPT: A Large Language Model for Financecited by 939
  5. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Modelscited by 785
  6. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  7. 2023A Comprehensive Overview of Large Language Modelscited by 648
  8. 2023Catastrophic Jailbreak of Open-source LLMs via Exploiting Generationcited by 451
  9. 2023Scalable Extraction of Training Data from (Production) Language Modelscited by 434
  10. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  11. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 321
  12. 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 285
38 more
  1. 2023Large Language Model Alignment: A Surveycited by 243
  2. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 237
  3. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 194
  4. 2023LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examplescited by 177
  5. 2024PLeak: Prompt Leaking Attacks against Large Language Model Applicationscited by 127
  6. 2023Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Modelscited by 94
  7. 2024Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Spacecited by 91
  8. 2024A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systemscited by 77
  9. 2023Composite Backdoor Attacks Against Large Language Modelscited by 73
  10. 2024When LLMs Meet Cybersecurity: A Systematic Literature Reviewcited by 71
  11. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 66
  12. 2023Unveiling Security, Privacy, and Ethical Concerns of ChatGPTcited by 53
  13. 2023LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Pluginscited by 51
  14. 2022Are Attribute Inference Attacks Just Imputation?cited by 49
  15. 2023Adversarial Attacks and Defenses in Large Language Models: Old and New Threatscited by 49
  16. 2024Persistent Pre-Training Poisoning of LLMscited by 48
  17. 2024Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Modelscited by 44
  18. 2023A Comprehensive Overview of Backdoor Attacks in Large Language Models within Communication Networkscited by 42
  19. 2023PoisonPrompt: Backdoor Attack on Prompt-based Large Language Modelscited by 42
  20. 2023Privacy Side Channels in Machine Learning Systemscited by 40
  21. 2023Demystifying RCE Vulnerabilities in LLM-Integrated Appscited by 37
  22. 2024Securing Large Language Models: Threats, Vulnerabilities and Responsible Practicescited by 37
  23. 2023Beyond the Safeguards: Exploring the Security Risks of ChatGPTcited by 36
  24. 2021MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AIcited by 35
  25. 2024Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Surveycited by 35
  26. 2024Large Language Models in Cybersecurity: State-of-the-Artcited by 34
  27. 2024Large Language Models for Education: A Surveycited by 34
  28. 2021On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Modelscited by 31
  29. 2023ChatGPT: Applications, Opportunities, and Threatscited by 28
  30. 2024What Was Your Prompt? A Remote Keylogging Attack on AI Assistantscited by 26
  31. 2024Jill Watson: A Virtual Teaching Assistant powered by ChatGPTcited by 24
  32. 2023Model Leeching: An Extraction Attack Targeting LLMscited by 22
  33. 2024Noisy Neighbors: Efficient membership inference attacks against LLMscited by 21
  34. 2023New Era of Artificial Intelligence in Education: Towards a Sustainable Multifaceted Revolutioncited by 20
  35. 2024Virtual Context: Enhancing Jailbreak Attacks with Special Token Injectioncited by 17
  36. 2024Vocabulary Attack to Hijack Large Language Model Applicationscited by 12
  37. 2023An Empirical Study on Using Large Language Models to Analyze Software Supply Chain Security Failurescited by 11
  38. 2022Threat Assessment in Machine Learning based Systemscited by 9

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detectioncited by 5
  2. 2026SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMscited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2025Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses
  2. 2026EduZone: A Framework for Evaluating LLM Safety for K-12 Students and Teachers
  3. 2024Risk and Response in Large Language Models: Evaluating Key Threat Categories
  4. 2025Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques
  5. 2024Security and Privacy Challenges of Large Language Models: A Survey
  6. 2024Exploring Vulnerabilities and Protections in Large Language Models: A Survey
  7. 2025A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations
  8. 2025Attack and defense techniques in large language models: A survey and new perspectives