Ai Dark Pattern Detection System For Fair Web And App Ux

• Author(s):

  A.Alagarh | V.Sanjay | E.Sundara Vignesh | S.Sriram

• Keywords:

• Abstract:

  The Increasing Prevalence Of Deceptive User Interface Designs, Commonly Referred To As Dark Patterns, Poses Significant Challenges To User Autonomy And Transparency In Digital Environments. These Patterns Manipulate Users Into Making Unintended Decisions, Such As Accepting Unnecessary Permissions Or Engaging With Misleading Offers. Traditional Detection Approaches Are Often Manual, Reactive, Or Limited In Scalability, Making Them Ineffective For Real-time User Protection. To Address These Limitations, This Project Proposes An Automated Dark Pattern Detection System Implemented As A Chrome Browser Extension Using Manifest V3 Architecture. The System Leverages A Rule-based Detection Mechanism Grounded In The FoSIP Framework To Identify Multiple Categories Of Manipulative Design, Including Social Engineering, Forced Actions, Interface Interference, Fake Discounts, And Persistent Elements. By Integrating Real-time DOM Analysis With The MutationObserver API, The Extension Dynamically Detects And Highlights Suspicious Elements Without Requiring User Interaction. Furthermore, The System Incorporates A Fairness Scoring Model That Quantifies The Ethical Quality Of Web Pages Based On Detected Patterns And Their Severity Levels. The Modular Architecture, Built Using Lightweight Web Technologies Such As JavaScript, HTML, And CSS, Ensures Scalability And Extensibility, Enabling Future Integration With AI-based Contextual Analysis. The Proposed Solution Provides A Proactive, User-centric Approach To Enhancing Transparency In Web Interactions, Promoting Ethical Design Practices, And Empowering Users To Make Informed Decisions While Browsing.

---

Other Details

• Paper id:

  IJSARTV12I4104849

• Published in:

  Volume: 12 Issue: 4 April 2026

• Publication Date:

  2026-04-03

Download Article