adgraph a graph based approach to ad and tracker blocking
play

AdGraph: A Graph-Based Approach to Ad and Tracker Blocking Umar - PowerPoint PPT Presentation

AdGraph: A Graph-Based Approach to Ad and Tracker Blocking Umar Iqbal, Peter Snyder, Shitong Zhu, Benjamin Livshits, Zhiyun Qian, and Zubair Shafiq IEEE Symposium on Security and Privacy, 2020 Online Advertising Advertising enables


  1. AdGraph: A Graph-Based Approach to Ad and Tracker Blocking Umar Iqbal, Peter Snyder, Shitong Zhu, Benjamin Livshits, Zhiyun Qian, and Zubair Shafiq IEEE Symposium on Security and Privacy, 2020

  2. Online Advertising Advertising enables “free”content Publishers show content Earn revenue with ads 1

  3. Online Advertising Advertising enables “free”content Publishers show content Earn revenue with ads Interactive Advertising Bureau (IAB) ‘19 2

  4. Online Advertising Advertising enables “free”content Publishers show content Earn revenue with ads Problems with online advertising ecosystem 3

  5. Online Advertising Advertising enables “free”content Publishers show content “I see ad ads for things I dream am ab about.” Earn revenue with ads “M “My y phone is s eave vesd sdropping on me me” Problems with online advertising ecosystem Privacy concerns – Behavioral targeting 4

  6. Online Advertising Advertising enables “free”content Publishers show content Earn revenue with ads Problems with online advertising ecosystem Privacy concerns – Behavioral targeting Performance issues – Slow page load 5

  7. Online Advertising Advertising enables “free”content Publishers show content Earn revenue with ads Problems with online advertising ecosystem Privacy concerns – Behavioral targeting Performance issues – Slow page load Malvertising 6

  8. Online Advertising Advertising enables “free”content Publishers show content Earn revenue with ads Problems with online advertising ecosystem Privacy concerns – Behavioral targeting Performance issues – Slow page load Malvertising Intrusive 7

  9. Online Advertising Advertising enables “free”content Publishers show content Earn revenue with ads Problems with online advertising ecosystem Privacy concerns – Behavioral targeting Performance issues – Slow page load Malvertising Intrusive Solution Ad & tracker blockers 8

  10. Outline State of Ad/Tracker Blocking Ads & Trackers Filter list blocking Machine learning based blocking AdGraph Graph-based representation Machine learning on graph representation Evaluation 9

  11. Outline State of Ad/Tracker Blocking Ads & Trackers Filter list blocking Machine learning based blocking 10

  12. What are Ads and Trackers? 11

  13. What are Ads and Trackers? Ads are audio-visual promotional content 12

  14. What are Ads and Trackers? Ads are audio-visual promotional content Trackers collect sensitive information Tracking Pixel 13

  15. What are Ads and Trackers? Ads are audio-visual promotional content Trackers collect sensitive information They are: Created with JavaScript Requested with HTTP Displayed with HTML Ads and trackers involve HTML, Network, and JavaScript Tracking Pixel 14

  16. JavaScript What are Ads and Trackers? Ads are audio-visual promotional content Trackers collect sensitive information They are: Created with JavaScript Tracking Pixel 15

  17. What are Ads and Trackers? Ads are audio-visual promotional content Trackers collect sensitive information HTTP They are: Created with JavaScript Requested with HTTP Tracking Pixel 16

  18. What are Ads and Trackers? Ads are audio-visual promotional content Trackers collect sensitive information HTML They are: Created with JavaScript Requested with HTTP Displayed with HTML Tracking Pixel 17

  19. JavaScript What are Ads and Trackers? Ads are audio-visual promotional content Trackers collect sensitive information HTML HTTP They are: Created with JavaScript Requested with HTTP Displayed with HTML Ads and trackers involve HTML, Network, and JavaScript Tracking Pixel 18

  20. Filter List Based Blocking Manually curated with crowdsourcing 19

  21. Filter List Based Blocking Manually curated with crowdsourcing Leads to scalability issue s 3 months to add new rules [Iqbal et al. ‘17] 20

  22. Filter List Based Blocking Manually curated with crowdsourcing Leads to scalability issue s 3.8 year to remove rules [Snyder et al. ‘20] 21

  23. Filter List Based Blocking Manually curated with crowdsourcing Leads to scalability issue s 90% rules are useless [Snyder et al. ‘20] 22

  24. Filter List Based Blocking Manually curated with crowdsourcing Leads to scalability issue s Operate at HTML/Network/JS layer in isolation 23

  25. Filter List Based Blocking Manually curated with crowdsourcing Block network request Leads to scalability issue s Operate at HTML/Network/JS layer in isolation Leads to accuracy issues 24

  26. Filter List Based Blocking Manually curated with crowdsourcing Block network request Leads to scalability issue s Operate at HTML/Network/JS layer in isolation Leads to accuracy issues Hide HTML elements 25

  27. Filter List Based Blocking Manually curated with crowdsourcing Block network request Leads to scalability issue s Operate at HTML/Network/JS layer in isolation Leads to accuracy issues Hide HTML elements Block script execution 26

  28. Filter List Based Blocking Manually curated with crowdsourcing Block network request Leads to scalability issue s Operate at HTML/Network/JS layer in isolation Leads to accuracy issues Hide HTML elements Block script execution 27

  29. Filter List Based Blocking Suffer from scalability issues Suffer from accuracy issues 28

  30. Machine Learning Based Blocking Network layer [Bhagavatula et al. 14, Gugelmann et al. ’15] HTTP header properties as features presence of words like “ad” cookies set by response 29

  31. Machine Learning Based Blocking Network layer [Bhagavatula et al. 14, Gugelmann et al. ’15] HTTP header properties as features presence of words like “ad” cookies set by response JavaScript layer [Wu et al. ‘16, Ikram et al. ‘17] JS API names as features document.cookie element.clientWidth 30

  32. Machine Learning Based Blocking Solve scalability issues 31

  33. Machine Learning Based Blocking Solve scalability issues Do not solve accuracy issues 32

  34. Outline AdGraph Graph-based representation Machine learning on graph representation Evaluation 33

  35. AdG AdGra raph ph �������������������� ���� �� ����� � ������� ������ �� ������ ����������������������� �������������������������� ��������������������������� ������������������� �������������������� ��������������������� ��������������������� �������������������������� ���������������������� ������������� ������������������ ����������������� 34

  36. AdGra AdG raph ph Graph-based cross-layer representation of ad/tracker behavior �������������������� ���� �� ����� � ������� ������ �� ������ ����������������������� �������������������������� ��������������������������� ������������������� �������������������� ��������������������� ��������������������� �������������������������� ���������������������� ������������� ������������������ ����������������� 35

  37. AdG AdGra raph ph Graph-based cross-layer ML to automatically learn representation of ad/tracker behavior ad/tracker behavior �������������������� ���� �� ����� � ������� ������ �� ������ ����������������������� �������������������������� ��������������������������� ������������������� �������������������� ��������������������� ��������������������� �������������������������� ���������������������� ������������� ������������������ ����������������� 36

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend