mlsanityData to 7 Oct 2026

Inducing Personality in LLM-Based Honeypot Agents: Measuring the Effect on Human-Like Agenda Generation

arXiv 2503.19752 ↗First posted 25 Mar 2025cs.AI cs.MAcited by 3

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

This paper presents SANDMAN, an architecture for cyber deception that leverages Language Agents to emulate convincing human simulacra. Our 'Deceptive Agents' serve as advanced cyber decoys, designed for high-fidelity engagement with attackers by extending the observation period of attack behaviours. Through experimentation, measurement, and analysis, we demonstrate how a prompt schema based on the five-factor model of personality systematically induces distinct 'personalities' in Large Language Models. Our results highlight the feasibility of persona-driven Language Agents for generating diverse, realistic behaviours, ultimately improving cyber deception strategies.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 16 of its 40 references that are in the map. First posted on arXiv 25 Mar 2025.

Builds on

16 of 40 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 15

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2015Continuous control with deep reinforcement learningcited by 3,279
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  5. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  6. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  7. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 300
  8. 2021Alignment of Language Agentscited by 167
  9. 2023Agents: An Open-source Framework for Autonomous Language Agentscited by 116
  10. 2023PentestGPT: An LLM-empowered Automatic Penetration Testing Toolcited by 94
  11. 2018Generative Adversarial User Model for Reinforcement Learning Based Recommendation Systemcited by 64
  12. 2024LLMParser: An Exploratory Study on Using Large Language Models for Log Parsingcited by 32
3 more
  1. 2017A Game-Theoretic Taxonomy and Survey of Defensive Deception for Cybersecurity and Privacycited by 22
  2. 2021Robust and Transferable Anomaly Detection in Log Data using Pre-Trained Language Modelscited by 12
  3. 2016Technical Aspects of Cyber Kill Chaincited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025FAIRGAME: a Framework for AI Agents Bias Recognition using Game Theorycited by 13
  2. 2025Strategic Communication and Language Bias in Multi-Agent LLM Coordinationcited by 3
  3. 2026When Numbers Start Talking: Implicit Numerical Coordination Among LLM-Based Agentscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Personality-Driven Decision-Making in LLM-Based Autonomous Agents
  2. 2023Deception Abilities Emerged in Large Language Models
  3. 2026Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
  4. 2026DecepEval: A Benchmark for Evaluating Deception in LLM Agents
  5. 2026Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games
  6. 2025Among Us: A Sandbox for Measuring and Detecting Agentic Deception
  7. 2026Structured Personality Control and Adaptation for LLM Agents
  8. 2025Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems