Organizations: Department of Computer Science and Technology, Tsinghua University, China · University of Southern California, USA · Shanghai Jiao Tong University, China · State Key Laboratory of Internet Architecture, Tsinghua University, China
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.
Figures & tables
Figure 1. MANA as a multimodal reasoning agent for efficient mobile ad detection, fusing heterogeneous signals to jointly reason about “where and how to go”.
Figure 2. Examples of different ad types: (a) integrated within the app interface as a banner; (b) shown as an intrusive interstitial that blocks normal interaction; (c) implemented as a “More Apps” list without standard SDK patterns, requiring semantic reasoning to recognize as advertising.
Figure 3. Screenshots of two example apps. The middle panels show the view-hierarchy nodes corresponding to the blue-boxed components in the screenshots, while red boxes highlight ad-related elements.
Figure 4. The system overview of MANA.
Figure 5
Figure 7. Cross-rendering consistency scheme, which combines Accessibility Service with visual techniques to produce semantically described actionable components for hierarchy-based and canvas-rendered apps.
Figure 8. Examples of MANA reasoning on a single UI screen. (a) a view-metadata case where hierarchical metadata identifies the “Other apps” button as a promotional redirection; (b) A visual cues case ( e . g ., “FREE COINS”) in a rendering app reveal advertising intent.
Figure 9. Cross-app regularities captured by memory. (a) and (b) both exhibit recurring ad-triggering patterns via the “Hidden Menu → More Apps” option, (c) shows the corresponding memory entry abstracted into a reusable representation.
Figure 10. An illustration of the structured prompt in MANA. The system prompt defines the task and heuristics, while the integrated prompt supplies multi-faceted context for decision-making.
Figure 11. Representative success case of MANA.
Figure 11Figure 12Figure 13
Figure 20. Automatic detection and analysis of malicious advertising by MANA. (a) A custom in-app ad is detected. (b) The interaction triggers a redirection to a suspicious website. (c) The system captures the ensuing browser warning, and (d) submits the URL to VirusTotal, which confirms it as malicious.
Figure 21. Case study on permission abuse.
Figure 22. Representative failure case of MANA.
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 23. An example of a hierarchy-based app.
Figure 24. An example of a hierarchy-based app with VLM-annotated UI element.
Online advertising studies how digital ads are targeted, ranked, priced, measured, and delivered while balancing budgets, business goals, and user interests.