Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight

• URL: http://arxiv.org/abs/2509.10723v1
• Date: Fri, 12 Sep 2025 22:26:31 GMT
• Title: Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight
• Authors: Jingyu Tang, Chaoran Chen, Jiawen Li, Zhiping Zhang, Bingcan Guo, Ibrahim Khalilov, Simret Araya Gebreegziabher, Bingsheng Yao, Dakuo Wang, Yanfang Ye, Tianshi Li, Ziang Xiao, Yaxing Yao, Toby Jia-Jun Li,
• Abstract summary: This study examines how agents, human participants, and human-AI teams respond to 16 types of dark patterns across diverse scenarios.<n>Phase 1 highlights that agents often fail to recognize dark patterns, and even when aware, prioritize task completion over protective action.<n>Phase 2 revealed divergent failure modes: humans succumb due to cognitive shortcuts and habitual compliance, while agents falter from procedural blind spots.
• Score: 51.53020962098759
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks from high-level intents, understanding how dark patterns affect agents is increasingly important. We present a two-phase empirical study examining how agents, human participants, and human-AI teams respond to 16 types of dark patterns across diverse scenarios. Phase 1 highlights that agents often fail to recognize dark patterns, and even when aware, prioritize task completion over protective action. Phase 2 revealed divergent failure modes: humans succumb due to cognitive shortcuts and habitual compliance, while agents falter from procedural blind spots. Human oversight improved avoidance but introduced costs such as attentional tunneling and cognitive load. Our findings show neither humans nor agents are uniformly resilient, and collaboration introduces new vulnerabilities, suggesting design needs for transparency, adjustable autonomy, and oversight.

Related papers

• Modeling Distinct Human Interaction in Web Agents [59.600507469754575]
  We introduce the task of modeling human intervention to support collaborative web task execution.<n>We identify four distinct patterns of user interaction with agents -- hands-off supervision, hands-on oversight, collaborative task-solving, and full user takeover.<n>We deploy these intervention-aware models in live web navigation agents and evaluate them in a user study, finding a 26.5% increase in user-rated agent usefulness.
  arXiv  Detail & Related papers  (2026-02-19T18:11:28Z)
• From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness [5.572574491501413]
  Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of actions with real-world impacts beyond text generation.<n>While persona-induced biases in text generation are well documented, their effects on agent task performance remain largely unexplored.<n>We present the first systematic case study showing that demographic-based persona assignments can alter LLM agents' behavior and degrade performance across diverse domains.
  arXiv  Detail & Related papers  (2026-01-21T02:43:07Z)
• Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI [9.383958408772694]
  We introduce an interface that enables neural transparency by exposing language model internals during chatbots design.<n>Our approach extracts behavioral trait vectors by computing differences in neural activations between contrastive system prompts that elicit opposing behaviors.<n>This work offers a path for how interpretability can be operationalized for non-technical users, establishing a foundation for safer, more aligned human-AI interactions.
  arXiv  Detail & Related papers  (2025-10-31T20:03:52Z)
• Investigating the Impact of Dark Patterns on LLM-Based Web Agents [16.297159088186888]
  We present the first study that investigates the impact of dark patterns on the decision-making process of LLM-based generalist web agents.<n>We introduce LiteAgent, a lightweight framework that automatically prompts agents to execute tasks.<n>We also present TrickyArena, a controlled environment comprising web applications from domains such as e-commerce, streaming services, and news platforms.
  arXiv  Detail & Related papers  (2025-10-20T21:26:26Z)
• The Agent Behavior: Model, Governance and Challenges in the AI Digital Age [13.689486430780518]
  Advancements in AI have led to agents in networked environments increasingly mirroring human behavior.<n>This paper proposes the "Network Behavior Lifecycle" model, which divides network behavior into 6 stages and systematically analyzes the behavioral differences between humans and agents at each stage.<n>The paper further introduces the "Agent for Agent (A4A)" paradigm and the "Human-Agent Behavioral Disparity (HABD)" model, which examine the fundamental distinctions between human and agent behaviors across 5 dimensions.
  arXiv  Detail & Related papers  (2025-08-20T04:24:55Z)
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks [58.959622170433725]
  BlindGuard is an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.<n>We show that BlindGuard effectively detects diverse attack types (i.e., prompt injection, memory poisoning, and tool attack) across multi-agent systems.
  arXiv  Detail & Related papers  (2025-08-11T16:04:47Z)
• Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation [52.6091162517921]
  INSIGHT is a two-stage framework for egocentric action anticipation.<n>In the first stage, INSIGHT focuses on extracting semantically rich features from hand-object interaction regions.<n>In the second stage, it introduces a reinforcement learning-based module that simulates explicit cognitive reasoning.
  arXiv  Detail & Related papers  (2025-08-03T12:52:27Z)
• Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations [60.63340688538124]
  Hallucination is a long-standing problem that has been actively investigated in Vision-Language Models (VLMs)<n>Existing research commonly attributes hallucinations to technical limitations or sycophancy bias, where the latter means the models tend to generate incorrect answers to align with user expectations.<n>In this work, we introduce a psychological taxonomy, categorizing VLMs' cognitive biases that lead to hallucinations, including sycophancy, logical inconsistency, and a newly identified VLMs behaviour: appeal to authority.
  arXiv  Detail & Related papers  (2025-07-03T19:03:16Z)
• HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models [30.596530112268848]
  We present the first systematic study of hallucinations in large language models performing long-horizon tasks under scene-task inconsistencies.<n>Our goal is to understand to what extent hallucinations occur, what types of inconsistencies trigger them, and how current models respond.
  arXiv  Detail & Related papers  (2025-06-18T02:13:41Z)
• Can you see how I learn? Human observers' inferences about Reinforcement Learning agents' learning processes [1.6874375111244329]
  Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers.<n>This work provides a data-driven understanding of the factors of human observers' understanding of the agent's learning process.
  arXiv  Detail & Related papers  (2025-06-16T15:04:27Z)
• Visual Agents as Fast and Slow Thinkers [88.1404921693082]
  We introduce FaST, which incorporates the Fast and Slow Thinking mechanism into visual agents.<n>FaST employs a switch adapter to dynamically select between System 1/2 modes.<n>It tackles uncertain and unseen objects by adjusting model confidence and integrating new contextual data.
  arXiv  Detail & Related papers  (2024-08-16T17:44:02Z)
• Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach [55.613461060997004]
  Large Language Models (LLMs) have catalyzed transformative advances across a spectrum of natural language processing tasks. We propose an innovative textitmetacognitive approach, dubbed textbfCLEAR, to equip LLMs with capabilities for self-aware error identification and correction.
  arXiv  Detail & Related papers  (2024-03-08T19:18:53Z)
• On the Difficulty of Defending Contrastive Learning against Backdoor Attacks [58.824074124014224]
  We show how contrastive backdoor attacks operate through distinctive mechanisms. Our findings highlight the need for defenses tailored to the specificities of contrastive backdoor attacks.
  arXiv  Detail & Related papers  (2023-12-14T15:54:52Z)
• Conveying Autonomous Robot Capabilities through Contrasting Behaviour Summaries [8.413049356622201]
  We present an adaptive search method for efficiently generating contrasting behaviour summaries. Our results indicate that adaptive search can efficiently identify informative contrasting scenarios that enable humans to accurately select the better performing agent.
  arXiv  Detail & Related papers  (2023-04-01T18:20:59Z)
• Affect-Aware Deep Belief Network Representations for Multimodal Unsupervised Deception Detection [3.04585143845864]
  unsupervised approach for detecting real-world, high-stakes deception in videos without requiring labels. This paper presents our novel approach for affect-aware unsupervised Deep Belief Networks (DBN) In addition to using facial affect as a feature on which DBN models are trained, we also introduce a DBN training procedure that uses facial affect as an aligner of audio-visual representations.
  arXiv  Detail & Related papers  (2021-08-17T22:07:26Z)

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.