Cover Image

On the Suitability of LLM-Driven Agents for Dark Pattern Audits

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Chen, Vekaria, Yash, Nithyanand, Rishab
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language Computers and Society Human-Computer Interaction
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Understanding Data Collection, Brokerage, and Spam in the Lead Marketing Ecosystem
by: Vekaria, Yash, et al.
Published: (2026)

LLM Novice Uplift on Dual-Use, In Silico Biology Tasks
by: Zhang, Chen Bo Calvin, et al.
Published: (2026)

Assessing LLM Response Quality in the Context of Technology-Facilitated Abuse
by: Prakash, Vijay, et al.
Published: (2026)

Keys on Doormats: Exposed API Credentials on the Web
by: Demir, Nurullah, et al.
Published: (2026)

NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey
by: Goswami, Dhiman, et al.
Published: (2026)

Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information
by: Zhan, Xiao, et al.
Published: (2025)

Learned, Lagged, LLM-splained: LLM Responses to End User Security Questions
by: Prakash, Vijay, et al.
Published: (2024)

PixelConfig: Longitudinal Measurement and Reverse-Engineering of Meta Pixel Configurations
by: Ghani, Abdullah, et al.
Published: (2026)

When Ads Become Profiles: Uncovering the Invisible Risk of Web Advertising at Scale with LLMs
by: Chen, Baiyu, et al.
Published: (2025)

Empowering Users in Digital Privacy Management through Interactive LLM-Based Agents
by: Sun, Bolun, et al.
Published: (2024)

Auditing the Compliance and Enforcement of Twitter's Advertising Policy
by: Vekaria, Yash, et al.
Published: (2023)

What Security and Privacy Transparency Users Need from Consumer-Facing Generative AI
by: Cao, Jiaxun, et al.
Published: (2026)

OpenAI's Approach to External Red Teaming for AI Models and Systems
by: Ahmad, Lama, et al.
Published: (2025)

Personhood Credentials: Human-Centered Design Recommendation Balancing Security, Usability, and Trust
by: Ide, Ayae, et al.
Published: (2025)

"Think First, Verify Always": Training Humans to Face AI Risks
by: Aydin, Yuksel
Published: (2025)

The Silicon Psyche: Anthropomorphic Vulnerabilities in Large Language Models
by: Canale, Giuseppe, et al.
Published: (2025)

PRISM: A Personalized, Rapid, and Immersive Skill Mastery framework for personalizing experiential learning through Generative AI
by: Lin, Yu-Zheng, et al.
Published: (2024)

To Patch or Not to Patch: Motivations, Challenges, and Implications for Cybersecurity
by: Nurse, Jason R. C.
Published: (2025)

RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models
by: Wang, Jiongxiao, et al.
Published: (2023)

Can LLM-Generated Misinformation Be Detected?
by: Chen, Canyu, et al.
Published: (2023)

From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents
by: Wu, Liangxuan, et al.
Published: (2025)

Hacc-Man: An Arcade Game for Jailbreaking LLMs
by: Valentim, Matheus, et al.
Published: (2024)

Beyond Words: On Large Language Models Actionability in Mission-Critical Risk Analysis
by: Esposito, Matteo, et al.
Published: (2024)

Emergent misalignment as prompt sensitivity: A research note
by: Wyse, Tim, et al.
Published: (2025)

Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents
by: Zhang, Zhiping, et al.
Published: (2025)

Stop Testing Attacks, Start Diagnosing Defenses: The Four-Checkpoint Framework Reveals Where LLM Safety Breaks
by: Dhabhi, Hayfa, et al.
Published: (2026)

Exploring User Security and Privacy Attitudes and Concerns Toward the Use of General-Purpose LLM Chatbots for Mental Health
by: Kwesi, Jabari, et al.
Published: (2025)

When Feasibility of Fairness Audits Relies on Willingness to Share Data: Examining User Acceptance of Multi-Party Computation Protocols for Fairness Monitoring
by: He, Changyang, et al.
Published: (2026)

Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents
by: Chen, Chaoran, et al.
Published: (2025)

The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections
by: Chen, Chaoran, et al.
Published: (2025)

"It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents
by: Zhang, Zhiping, et al.
Published: (2023)

Access Over Deception: Fighting Deceptive Patterns through Accessibility
by: Pellkvist, Tobias, et al.
Published: (2026)

Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots
by: Zhou, Jijie, et al.
Published: (2024)

Learning from Mistakes: Can LLM Self-Recover after Misalignment?
by: Sorokoletova, Olga E., et al.
Published: (2026)

Current state of LLM Risks and AI Guardrails
by: Ayyamperumal, Suriya Ganesh, et al.
Published: (2024)

V.O.I.C.E (Voice, Ownership, Identity, Control, Expression): Risk Taxonomy of Synthetic Voice Generation From Empirical Data
by: Sharma, Tanusree, et al.
Published: (2026)

Intolerable Risk Threshold Recommendations for Artificial Intelligence
by: Raman, Deepika, et al.
Published: (2025)

"Is it always watching? Is it always listening?" Exploring Contextual Privacy and Security Concerns Toward Domestic Social Robots
by: Bell, Henry, et al.
Published: (2025)

Enabling Cyber Security Education through Digital Twins and Generative AI
by: Barletta, Vita Santa, et al.
Published: (2025)

Human-AI Collaboration in Cloud Security: Cognitive Hierarchy-Driven Deep Reinforcement Learning
by: Aref, Zahra, et al.
Published: (2025)