mlsanityData to 13 Oct 2026

The Road of Adaptive AI for Precision in Cybersecurity

arXiv 2512.06048 ↗First posted 5 Dec 2025cs.CR cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Cybersecurity's evolving complexity presents unique challenges and opportunities for AI research and practice. This paper shares key lessons and insights from designing, building, and operating production-grade GenAI pipelines in cybersecurity, with a focus on the continual adaptation required to keep pace with ever-shifting knowledge bases, tooling, and threats. Our goal is to provide an actionable perspective for AI practitioners and industry stakeholders navigating the frontier of GenAI for cybersecurity, with particular attention to how different adaptation mechanisms complement each other in end-to-end systems. We present practical guidance derived from real-world deployments, propose best practices for leveraging retrieval- and model-level adaptation, and highlight open research directions for making GenAI more robust, precise, and auditable in cyber defense.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 53 of its 77 references that are in the map. First posted on arXiv 5 Dec 2025.

Builds on

53 of 77 references.

References · 53

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2020Language Models are Few-Shot Learnerscited by 32,320
  3. 2022Training language models to follow instructions with human feedbackcited by 15,856
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,979
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,376
  6. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  7. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,221
  8. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,107
  9. 2017Inductive Representation Learning on Large Graphscited by 6,303
  10. 2016Overcoming catastrophic forgetting in neural networkscited by 4,753
  11. 2022Large Language Models are Zero-Shot Reasonerscited by 4,348
  12. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,797
38 more
  1. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,765
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,412
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,388
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,367
  5. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,197
  6. 2022Locating and Editing Factual Associations in GPTcited by 2,650
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,196
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,131
  9. 2022Survey of Hallucination in Natural Language Generationcited by 2,068
  10. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,945
  11. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,815
  12. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,777
  13. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,594
  14. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,556
  15. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,424
  16. 2021Improving language models by retrieving from trillions of tokenscited by 1,286
  17. 2022Mass-Editing Memory in a Transformercited by 990
  18. 2023ChatDev: Communicative Agents for Software Developmentcited by 901
  19. 2022Large Language Models Can Self-Improvecited by 659
  20. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 630
  21. 2023Active Retrieval Augmented Generationcited by 510
  22. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 426
  23. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 367
  24. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 233
  25. 2023Continual Pre-training of Language Modelscited by 195
  26. 2024Continual Learning for Large Language Models: A Surveycited by 144
  27. 2024Simple and Scalable Strategies to Continually Pre-train Large Language Modelscited by 125
  28. 2025Context Length Alone Hurts LLM Performance Despite Perfect Retrievalcited by 120
  29. 2024Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilizationcited by 99
  30. 2023PentestGPT: An LLM-empowered Automatic Penetration Testing Toolcited by 96
  31. 2024Large Language Models for Cyber Security: A Systematic Literature Reviewcited by 68
  32. 2023Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Studycited by 63
  33. 2024Investigating Continual Pretraining in Large Language Models: Insights and Implicationscited by 56
  34. 2024Scaling Retrieval-Based Language Models with a Trillion-Token Datastorecited by 54
  35. 2018FIRST: A Framework for Optimizing Information Quality in Mobile Crowdsensing Systemscited by 50
  36. 2025A Survey on Agentic Security: Applications, Threats and Defensescited by 19
  37. 2024Actionable Cyber Threat Intelligence using Knowledge Graphs and Large Language Modelscited by 14
  38. 2025Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMscited by 13

50 most cited of 53 All 53 (JSON)

Built on by

Not cited yet.