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

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

URL: http://arxiv.org/abs/2503.19752v1
Date: Tue, 25 Mar 2025 15:16:35 GMT
Title: Inducing Personality in LLM-Based Honeypot Agents: Measuring the Effect on Human-Like Agenda Generation
Authors: Lewis Newsham, Ryan Hyland, Daniel Prince,
Abstract summary: SANDMAN is an architecture for cyber deception that leverages Language Agents to emulate convincing human simulacra.<n>Our 'Deceptive Agents' serve as advanced cyber decoys, designed for high-fidelity engagement with attackers.
Score: 0.22499166814992438
License: http://creativecommons.org/licenses/by/4.0/
Abstract: 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.

Related papers

Model-Agnostic Policy Explanations with Large Language Models [6.405870799906393]
We propose a method for generating natural language explanations of agent behavior based only on observed states and actions. Our approach learns a locally interpretable surrogate model of the agent's behavior from observations. We find that participants in a user study more accurately predicted the agent's future actions when given our explanations.
arXiv Detail & Related papers (2025-04-08T02:56:02Z)
Personality-Driven Decision-Making in LLM-Based Autonomous Agents [0.276240219662896]
This study presents a novel method for measuring and evaluating how induced personality traits affect task selection processes. Our results reveal distinct task-selection patterns aligned with induced OCEAN attributes, underscoring the feasibility of designing highly plausible Deceptive Agents for proactive cyber defense strategies.
arXiv Detail & Related papers (2025-04-01T12:36:28Z)
Generative Agent Simulations of 1,000 People [56.82159813294894]
We present a novel agent architecture that simulates the attitudes and behaviors of 1,052 real individuals. The generative agents replicate participants' responses on the General Social Survey 85% as accurately as participants replicate their own answers. Our architecture reduces accuracy biases across racial and ideological groups compared to agents given demographic descriptions.
arXiv Detail & Related papers (2024-11-15T11:14:34Z)
PersLLM: A Personified Training Approach for Large Language Models [66.16513246245401]
We propose PersLLM, integrating psychology-grounded principles of personality: social practice, consistency, and dynamic development. We incorporate personality traits directly into the model parameters, enhancing the model's resistance to induction, promoting consistency, and supporting the dynamic evolution of personality.
arXiv Detail & Related papers (2024-07-17T08:13:22Z)
LLMs Simulate Big Five Personality Traits: Further Evidence [51.13560635563004]
We analyze the personality traits simulated by Llama2, GPT4, and Mixtral. This contributes to the broader understanding of the capabilities of LLMs to simulate personality traits.
arXiv Detail & Related papers (2024-01-31T13:45:25Z)
Understanding Your Agent: Leveraging Large Language Models for Behavior Explanation [7.647395374489533]
We propose an approach to generate natural language explanations for an agent's behavior based only on observations of states and actions. We show that our approach generates explanations as helpful as those produced by a human domain expert.
arXiv Detail & Related papers (2023-11-29T20:16:23Z)
Explaining Agent Behavior with Large Language Models [7.128139268426959]
We propose an approach to generate natural language explanations for an agent's behavior based only on observations of states and actions. We show how a compact representation of the agent's behavior can be learned and used to produce plausible explanations.
arXiv Detail & Related papers (2023-09-19T06:13:24Z)
User Behavior Simulation with Large Language Model based Agents [116.74368915420065]
We propose an LLM-based agent framework and design a sandbox environment to simulate real user behaviors. Based on extensive experiments, we find that the simulated behaviors of our method are very close to the ones of real humans.
arXiv Detail & Related papers (2023-06-05T02:58:35Z)
Generative Agents: Interactive Simulacra of Human Behavior [86.1026716646289]
We introduce generative agents--computational software agents that simulate believable human behavior. We describe an architecture that extends a large language model to store a complete record of the agent's experiences. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims.
arXiv Detail & Related papers (2023-04-07T01:55:19Z)
Backprop-Free Reinforcement Learning with Active Neural Generative Coding [84.11376568625353]
We propose a computational framework for learning action-driven generative models without backpropagation of errors (backprop) in dynamic environments. We develop an intelligent agent that operates even with sparse rewards, drawing inspiration from the cognitive theory of planning as inference. The robust performance of our agent offers promising evidence that a backprop-free approach for neural inference and learning can drive goal-directed behavior.
arXiv Detail & Related papers (2021-07-10T19:02:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.