Building UI/UX Dataset for Dark Pattern Detection and YOLOv12x-based Real-Time Object Recognition Detection System

TL;DR

This work addresses the need for proactive, real-time detection of visual dark patterns in UI/UX. It introduces a proprietary dataset of 4,066 UI screenshots across six sectors, labeled for five UI components, and publicly releases it to the research community. The authors train an enhanced YOLOv12x detector via transfer learning, achieving 92.8% mAP@50 with 40.5 FPS, demonstrating practical real-time applicability. The combination of a large, diverse visual dataset and a high-speed detector provides a solid foundation for detecting deceptive UI patterns to support regulation and user protection.

Abstract

With the accelerating pace of digital transformation and the widespread adoption of online platforms, both social and technical concerns regarding dark patterns-user interface designs that undermine users' ability to make informed and rational choices-have become increasingly prominent. As corporate online platforms grow more sophisticated in their design strategies, there is a pressing need for proactive and real-time detection technologies that go beyond the predominantly reactive approaches employed by regulatory authorities. In this paper, we propose a visual dark pattern detection framework that improves both detection accuracy and real-time performance. To this end, we constructed a proprietary visual object detection dataset by manually collecting 4,066 UI/UX screenshots containing dark patterns from 194 websites across six major industrial sectors in South Korea and abroad. The collected images were annotated with five representative UI components commonly associated with dark patterns: Button, Checkbox, Input Field, Pop-up, and QR Code. This dataset has been publicly released to support further research and development in the field. To enable real-time detection, this study adopted the YOLOv12x object detection model and applied transfer learning to optimize its performance for visual dark pattern recognition. Experimental results demonstrate that the proposed approach achieves a high detection accuracy of 92.8% in terms of mAP@50, while maintaining a real-time inference speed of 40.5 frames per second (FPS), confirming its effectiveness for practical deployment in online environments. Furthermore, to facilitate future research and contribute to technological advancements, the dataset constructed in this study has been made publicly available at https://github.com/B4E2/B4E2-DarkPattern-YOLO-DataSet.

Figures (4)

• Figure 1: Collection of Raw Data on Dark Patterns
• Figure 2: Overview of Data Collection Process (Left) and Labeled Dataset Examples (Right)
• Figure 3: YOLO Detection Pseudo-code
• Figure 4: Training Implementation Code