# Coherence-driven inference for cybersecurity

arXiv: https://arxiv.org/abs/2509.18520 · HTML: https://mlsanity.com/paper/2509.18520/

## 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 (most cited first, 16 of 16)

- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens](https://mlsanity.com/paper/2401.17377/) (2024)
- [On the Existence of Simpler Machine Learning Models](https://mlsanity.com/paper/1908.01755/) (2019)
- [From Statistical Relational to Neurosymbolic Artificial Intelligence: a Survey](https://mlsanity.com/paper/2108.11451/) (2021)
- [On Limitations of the Transformer Architecture](https://mlsanity.com/paper/2402.08164/) (2024)
- [Neuro-Symbolic Artificial Intelligence: Current Trends](https://mlsanity.com/paper/2105.05330/) (2021)
- [Transformers on Markov Data: Constant Depth Suffices](https://mlsanity.com/paper/2407.17686/) (2024)
- [Cyber-Zero: Training Cybersecurity Agents without Runtime](https://mlsanity.com/paper/2508.00910/) (2025)
- [Machine learning and information theory concepts towards an AI Mathematician](https://mlsanity.com/paper/2403.04571/) (2024)
- [Getting from Generative AI to Trustworthy AI: What LLMs might learn from Cyc](https://mlsanity.com/paper/2308.04445/) (2023)
- [Spectral Sparsification of Hypergraphs](https://mlsanity.com/paper/1807.04974/) (2018)
- [Prospects for inconsistency detection using large language models and sheaves](https://mlsanity.com/paper/2401.16713/) (2024)
- [From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs](https://mlsanity.com/paper/2506.13434/) (2025)
- [CmdCaliper: A Semantic-Aware Command-Line Embedding Model and Dataset for Security Research](https://mlsanity.com/paper/2411.01176/) (2024)
- [Benchmarking graph construction by large language models for coherence-driven inference](https://mlsanity.com/paper/2502.13953/) (2025)
- [Tight Bounds for Sparsifying Random CSPs](https://mlsanity.com/paper/2508.13345/) (2025)

## 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.