Human Decision-making is Susceptible to AI-driven Manipulation
- URL: http://arxiv.org/abs/2502.07663v1
- Date: Tue, 11 Feb 2025 15:56:22 GMT
- Title: Human Decision-making is Susceptible to AI-driven Manipulation
- Authors: Sahand Sabour, June M. Liu, Siyang Liu, Chris Z. Yao, Shiyao Cui, Xuanming Zhang, Wen Zhang, Yaru Cao, Advait Bhat, Jian Guan, Wei Wu, Rada Mihalcea, Tim Althoff, Tatia M. C. Lee, Minlie Huang,
- Abstract summary: AI systems may exploit users' cognitive biases and emotional vulnerabilities to steer them toward harmful outcomes.
This study examined human susceptibility to such manipulation in financial and emotional decision-making contexts.
- Score: 71.20729309185124
- License:
- Abstract: Artificial Intelligence (AI) systems are increasingly intertwined with daily life, assisting users in executing various tasks and providing guidance on decision-making. This integration introduces risks of AI-driven manipulation, where such systems may exploit users' cognitive biases and emotional vulnerabilities to steer them toward harmful outcomes. Through a randomized controlled trial with 233 participants, we examined human susceptibility to such manipulation in financial (e.g., purchases) and emotional (e.g., conflict resolution) decision-making contexts. Participants interacted with one of three AI agents: a neutral agent (NA) optimizing for user benefit without explicit influence, a manipulative agent (MA) designed to covertly influence beliefs and behaviors, or a strategy-enhanced manipulative agent (SEMA) employing explicit psychological tactics to reach its hidden objectives. By analyzing participants' decision patterns and shifts in their preference ratings post-interaction, we found significant susceptibility to AI-driven manipulation. Particularly, across both decision-making domains, participants interacting with the manipulative agents shifted toward harmful options at substantially higher rates (financial, MA: 62.3%, SEMA: 59.6%; emotional, MA: 42.3%, SEMA: 41.5%) compared to the NA group (financial, 35.8%; emotional, 12.8%). Notably, our findings reveal that even subtle manipulative objectives (MA) can be as effective as employing explicit psychological strategies (SEMA) in swaying human decision-making. By revealing the potential for covert AI influence, this study highlights a critical vulnerability in human-AI interactions, emphasizing the need for ethical safeguards and regulatory frameworks to ensure responsible deployment of AI technologies and protect human autonomy.
Related papers
- Engaging with AI: How Interface Design Shapes Human-AI Collaboration in High-Stakes Decision-Making [8.948482790298645]
We examine how various decision-support mechanisms impact user engagement, trust, and human-AI collaborative task performance.
Our findings reveal that mechanisms like AI confidence levels, text explanations, and performance visualizations enhanced human-AI collaborative task performance.
arXiv Detail & Related papers (2025-01-28T02:03:00Z) - Raising the Stakes: Performance Pressure Improves AI-Assisted Decision Making [57.53469908423318]
We show the effects of performance pressure on AI advice reliance when laypeople complete a common AI-assisted task.
We find that when the stakes are high, people use AI advice more appropriately than when stakes are lower, regardless of the presence of an AI explanation.
arXiv Detail & Related papers (2024-10-21T22:39:52Z) - Combining AI Control Systems and Human Decision Support via Robustness and Criticality [53.10194953873209]
We extend a methodology for adversarial explanations (AE) to state-of-the-art reinforcement learning frameworks.
We show that the learned AI control system demonstrates robustness against adversarial tampering.
In a training / learning framework, this technology can improve both the AI's decisions and explanations through human interaction.
arXiv Detail & Related papers (2024-07-03T15:38:57Z) - Beyond Recommender: An Exploratory Study of the Effects of Different AI
Roles in AI-Assisted Decision Making [48.179458030691286]
We examine three AI roles: Recommender, Analyzer, and Devil's Advocate.
Our results show each role's distinct strengths and limitations in task performance, reliance appropriateness, and user experience.
These insights offer valuable implications for designing AI assistants with adaptive functional roles according to different situations.
arXiv Detail & Related papers (2024-03-04T07:32:28Z) - Assessing Large Language Models' ability to predict how humans balance
self-interest and the interest of others [0.0]
Generative artificial intelligence (AI) holds enormous potential to revolutionize decision-making processes.
By leveraging generative AI, humans can benefit from data-driven insights and predictions.
However, for AI to be a reliable assistant for decision-making it is crucial that it is able to capture the balance between self-interest and the interest of others.
arXiv Detail & Related papers (2023-07-21T13:23:31Z) - Knowing About Knowing: An Illusion of Human Competence Can Hinder
Appropriate Reliance on AI Systems [13.484359389266864]
This paper addresses whether the Dunning-Kruger Effect (DKE) can hinder appropriate reliance on AI systems.
DKE is a metacognitive bias due to which less-competent individuals overestimate their own skill and performance.
We found that participants who overestimate their performance tend to exhibit under-reliance on AI systems.
arXiv Detail & Related papers (2023-01-25T14:26:10Z) - A Cognitive Framework for Delegation Between Error-Prone AI and Human
Agents [0.0]
We investigate the use of cognitively inspired models of behavior to predict the behavior of both human and AI agents.
The predicted behavior is used to delegate control between humans and AI agents through the use of an intermediary entity.
arXiv Detail & Related papers (2022-04-06T15:15:21Z) - A Case for Humans-in-the-Loop: Decisions in the Presence of Erroneous
Algorithmic Scores [85.12096045419686]
We study the adoption of an algorithmic tool used to assist child maltreatment hotline screening decisions.
We first show that humans do alter their behavior when the tool is deployed.
We show that humans are less likely to adhere to the machine's recommendation when the score displayed is an incorrect estimate of risk.
arXiv Detail & Related papers (2020-02-19T07:27:32Z) - Effect of Confidence and Explanation on Accuracy and Trust Calibration
in AI-Assisted Decision Making [53.62514158534574]
We study whether features that reveal case-specific model information can calibrate trust and improve the joint performance of the human and AI.
We show that confidence score can help calibrate people's trust in an AI model, but trust calibration alone is not sufficient to improve AI-assisted decision making.
arXiv Detail & Related papers (2020-01-07T15:33:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.