MANA: Towards Efficient Mobile Ad Detection via Multimodal Agentic UI Navigation

TL;DR

MANA is a multimodal agentic framework that enhances mobile ad detection by integrating static, visual, temporal, and experiential signals for efficient and robust UI exploration, outperforming existing methods.

Contribution

It introduces the first agentic multimodal reasoning framework for mobile ad detection, combining multiple signals for improved accuracy and efficiency.

Findings

Achieves state-of-the-art detection accuracy with 30.5%-56.3% improvement.

Reduces exploration steps by 29.7%-63.3%.

Effectively uncovers obfuscated and malicious ads.

Abstract

Mobile advertising dominates app monetization but introduces risks ranging from intrusive user experience to malware delivery. Existing detection methods rely either on static analysis, which misses runtime behaviors, or on heuristic UI exploration, which struggles with sparse and obfuscated ads. In this paper, we present MANA, the first agentic multimodal reasoning framework for mobile ad detection. MANA integrates static, visual, temporal, and experiential signals into a reasoning-guided navigation strategy that determines not only how to traverse interfaces but also where to focus, enabling efficient and robust exploration. We implement and evaluate MANA on commercial smartphones over 200 apps, achieving state-of-the-art accuracy and efficiency. Compared to baselines, it improves detection accuracy by 30.5%-56.3% and reduces exploration steps by 29.7%-63.3%. Case studies further demonstrate its ability to uncover obfuscated and malicious ads, underscoring its practicality for mobile ad auditing and its potential for broader runtime UI analysis (e.g., permission abuse). Code and dataset are available at https://github.com/MANA-2026/MANA.