mlsanityData to 14 Oct 2026

Coherence-driven inference for cybersecurity

arXiv 2509.18520 ↗First posted 23 Sep 2025cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) can compile weighted graphs on natural language data to enable automatic coherence-driven inference (CDI) relevant to red and blue team operations in cybersecurity. This represents an early application of automatic CDI that holds near- to medium-term promise for decision-making in cybersecurity and eventually also for autonomous blue team operations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 43 references that are in the map. First posted on arXiv 23 Sep 2025.

Builds on

16 of 43 references.

References · 16

  1. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 302
  2. 2024Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokenscited by 153
  3. 2019On the Existence of Simpler Machine Learning Modelscited by 89
  4. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
  5. 2024On Limitations of the Transformer Architecturecited by 63
  6. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
  7. 2024Transformers on Markov Data: Constant Depth Sufficescited by 27
  8. 2025Cyber-Zero: Training Cybersecurity Agents without Runtimecited by 22
  9. 2024Machine learning and information theory concepts towards an AI Mathematiciancited by 20
  10. 2023Getting from Generative AI to Trustworthy AI: What LLMs might learn from Cyccited by 19
  11. 2018Spectral Sparsification of Hypergraphscited by 10
  12. 2024Prospects for inconsistency detection using large language models and sheavescited by 10
4 more
  1. 2025From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMscited by 10
  2. 2024CmdCaliper: A Semantic-Aware Command-Line Embedding Model and Dataset for Security Researchcited by 5
  3. 2025Benchmarking graph construction by large language models for coherence-driven inferencecited by 2
  4. 2025Tight Bounds for Sparsifying Random CSPscited by 1

Built on by

Not cited yet.