[Paper Review] MyAdChoices: Bringing Transparency and Control to Online Advertising

Javier Parra‐Arnau, Jagdish Prasad Achara+1 more|arXiv (Cornell University)|Feb 5, 2016

Privacy, Security, and Data Protection31 references20 citations

TL;DR

This paper proposes MyAdChoices, a browser extension that enables users to exert fine-grained control over online advertising by visualizing and managing behavioral targeting and tracking preferences. It combines transparency with user control through a robust optimization framework, demonstrating feasibility in real-world deployment and showing that users can make informed, equitable choices about ads without resorting to blanket blocking.

ABSTRACT

The intrusiveness and the increasing invasiveness of online advertising have, in the last few years, raised serious concerns regarding user privacy and Web usability. As a reaction to these concerns, we have witnessed the emergence of a myriad of ad-blocking and anti-tracking tools, whose aim is to return control to users over advertising. The problem with these technologies, however, is that they are extremely limited and radical in their approach: users can only choose either to block or allow all ads. With around 200 million people regularly using these tools, the economic model of the Web ---in which users get content free in return for allowing advertisers to show them ads--- is at serious peril. In this paper, we propose a smart Web technology that aims at bringing transparency to online advertising, so that users can make an informed and equitable decision regarding ad blocking. The proposed technology is implemented as a Web-browser extension and enables users to exert fine-grained control over advertising, thus providing them with certain guarantees in terms of privacy and browsing experience, while preserving the Internet economic model. Experimental results in a real environment demonstrate the suitability and feasibility of our approach, and provide preliminary findings on behavioral targeting from real user browsing profiles.

Motivation & Objective

• To address the growing user concern over invasive online advertising and the widespread use of ad blockers that threaten the web's economic model.
• To provide users with real, informed control over behavioral targeting and tracking, moving beyond the binary choice of blocking all ads.
• To design a system that balances user privacy, Web usability, and the sustainability of free online content.
• To implement a feasible, transparent mechanism for users to understand and manage how their browsing data is used for advertising.
• To evaluate the system's practicality and user behavior through real-world deployment and analysis of browsing profiles.

Proposed method

• The system uses a browser extension to detect and categorize ads based on landing page content, enabling users to classify ads by topic and intent.
• It employs a robust minimax detection framework based on linear programming to estimate user preferences under uncertainty, using a polyhedral uncertainty set derived from clickstream data.
• The method models user preferences using a probability mass function (PMF) over topic categories, updated incrementally as users browse.
• It enforces constraints on minimum and maximum ad exposure per category using a confidence interval approach, ensuring user preferences are respected.
• The system uses optical character recognition (OCR) as a future enhancement to identify ads without requiring landing page access.
• It introduces a minimized private-mode window to display ad transparency information, reducing user disruption.

Experimental results

Research questions

• RQ1 Can users be given meaningful, fine-grained control over online advertising without resorting to complete ad blocking?
• RQ2 How can transparency in behavioral targeting and tracking be effectively implemented in a real-world browser environment?
• RQ3 What is the feasibility of using robust optimization to model user preferences under uncertainty in ad exposure?
• RQ4 How do real user browsing profiles behave in terms of behavioral targeting, and can they be reliably modeled?
• RQ5 Can a system be built that preserves the economic model of free web content while respecting user privacy and usability?

Key findings

• The proposed system is technically feasible and can be implemented as a browser extension that integrates with real browsing behavior.
• Experimental results in a real environment confirm the suitability and practicality of the approach for real-time ad transparency and control.
• The system successfully models user preferences using an incremental, uncertainty-aware optimization framework that maintains consistency across user browsing sessions.
• Preliminary analysis of real user browsing profiles reveals patterns in behavioral targeting, supporting the need for user-centric control mechanisms.
• The system's design avoids the limitations of current ad blockers by offering nuanced control instead of binary blocking, thus preserving the web's ad-supported model.
• The use of linear programming and robust minimax detection ensures that user preferences are enforced even under uncertain or incomplete data.