Automatically Detecting Online Deceptive Patterns in Real-time

2024-11-11

arXiv.org

AI Summary

Deceptive patterns (DPs) in digital interfaces widely exploit cognitive biases to induce involuntary user decisions, yet existing detection solutions lack real-time, privacy-preserving capabilities. This paper introduces AutoBot—the first lightweight, browser-side Chrome extension designed for on-device DP detection. It employs a two-stage, vision-and-text-context fusion framework that localizes DP interaction elements solely from webpage screenshots, without accessing HTML source code or requiring cloud communication—ensuring strong privacy guarantees and low latency. The method integrates a compact language model, computer vision–based object localization, and optimized on-device inference. Experiments on real-world websites demonstrate high detection accuracy; AutoBot significantly improves user awareness of DPs and provides regulators with an interpretable, deployable tool for DP compliance auditing.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Humans and AI: Intelligent User Interfaces

Application Category

• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Economics, Online Markets and Human Computation: Sustainability of Web economics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Deceptive patterns (DPs) in digital interfaces manipulate users into making unintended decisions, exploiting cognitive biases and psychological vulnerabilities. These patterns have become ubiquitous across various digital platforms. While efforts to mitigate DPs have emerged from legal and technical perspectives, a significant gap in usable solutions that empower users to identify and make informed decisions about DPs in real-time remains. In this work, we introduce AutoBot, an automated, deceptive pattern detector that analyzes websites' visual appearances using machine learning techniques to identify and notify users of DPs in real-time. AutoBot employs a two-staged pipeline that processes website screenshots, identifying interactable elements and extracting textual features without relying on HTML structure. By leveraging a custom language model, AutoBot understands the context surrounding these elements to determine the presence of deceptive patterns. We implement AutoBot as a lightweight Chrome browser extension that performs all analyses locally, minimizing latency and preserving user privacy. Through extensive evaluation, we demonstrate AutoBot's effectiveness in enhancing users' ability to navigate digital environments safely while providing a valuable tool for regulators to assess and enforce compliance with DP regulations.

Problem

• Detecting deceptive patterns in digital interfaces automatically
• Identifying manipulative elements exploiting cognitive biases
• Providing real-time user notifications about deceptive practices

Innovation

• Machine learning analyzes visual elements
• Custom language model understands context
• Lightweight browser extension ensures privacy