# Resistance Against Manipulative AI: key factors and possible actions

arXiv: https://arxiv.org/abs/2404.14230 · HTML: https://mlsanity.com/paper/2404.14230/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2024.

## Built on by (most cited first, 9 of 9)

- [Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications](https://mlsanity.com/paper/2411.06837/) (2024)
- [Human Decision-making is Susceptible to AI-driven Manipulation](https://mlsanity.com/paper/2502.07663/) (2025)
- [The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses](https://mlsanity.com/paper/2411.06008/) (2024)
- [Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks](https://mlsanity.com/paper/2505.19806/) (2025)
- [ChatbotManip: A Dataset to Facilitate Evaluation and Oversight of Manipulative Chatbot Behaviour](https://mlsanity.com/paper/2506.12090/) (2025)
- [PRISON: Unmasking the Criminal Potential of Large Language Models](https://mlsanity.com/paper/2506.16150/) (2025)
- [From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models](https://mlsanity.com/paper/2601.15690/) (2026)
- [Assessing AI-Generated vs. Human-Authored Spear Phishing SMS Attacks: An Empirical Study](https://mlsanity.com/paper/2406.13049/) (2024)
- [Train Yourself as an LLM: Exploring Effects of AI Literacy on Persuasion via Role-playing LLM Training](https://mlsanity.com/paper/2604.02637/) (2026)

## Abstract (arXiv)

If AI is the new electricity, what should we do to keep ourselves from getting electrocuted? In this work, we explore factors related to the potential of large language models (LLMs) to manipulate human decisions. We describe the results of two experiments designed to determine what characteristics of humans are associated with their susceptibility to LLM manipulation, and what characteristics of LLMs are associated with their manipulativeness potential. We explore human factors by conducting user studies in which participants answer general knowledge questions using LLM-generated hints, whereas LLM factors by provoking language models to create manipulative statements. Then, we analyze their obedience, the persuasion strategies used, and the choice of vocabulary. Based on these experiments, we discuss two actions that can protect us from LLM manipulation. In the long term, we put AI literacy at the forefront, arguing that educating society would minimize the risk of manipulation and its consequences. We also propose an ad hoc solution, a classifier that detects manipulation of LLMs - a Manipulation Fuse.