pribots
play

PriBots Conversational Privacy with Chatbots Hamza Harkous 1 , - PowerPoint PPT Presentation

Aug 20, 2022 •201 likes •708 views

PriBots Conversational Privacy with Chatbots Hamza Harkous 1 , Kassem Fawaz 2 , Kang. G. Shin 2 , Karl Aberer 1 1 EPFL; 2 University of Michigan Workshop on the Future of Privacy Notices and Indicators, SOUPS 2016 Privacy Notice: Current State 2

  1. PriBots Conversational Privacy with Chatbots Hamza Harkous 1 , Kassem Fawaz 2 , Kang. G. Shin 2 , Karl Aberer 1 1 EPFL; 2 University of Michigan Workshop on the Future of Privacy Notices and Indicators, SOUPS 2016

  2. Privacy Notice: Current State 2

  3. Privacy Notice: Current State legally binding Dual Role: human understandable 2

  4. Privacy Notice: Current State legally binding Dual Role: human understandable Can we split these roles? 2

  5. Standardization 3

  6. Standardization Summarization 3

  7. Standardization Summarization Challenges one size fits all user education 3

  8. Privacy Choice: Current State 4

  9. Privacy Choice: Current State fragmented ecosystem di fg icult to find 4

  10. Conversation-first Interfaces 5

  11. The Rise of Conversational UI 6

  12. PriBots: Conversational Privacy Bots | Message 7

  13. PriBots: Conversational Privacy Bots | Message 7

  14. PriBots: Conversational Privacy Bots Appeal to new tech adopters | Message 7

  15. PriBots: Conversational Privacy Bots Appeal to new tech adopters Appeal to existing users | Message 7

  16. PriBots: Conversational Privacy Bots Appeal to new tech adopters Appeal to existing users | Message An intuitive way to 1. communicate privacy policies 2. adjust privacy preferences 7

  17. 1- Communicating Privacy Policies 8

  18. Channel 9

  19. Channel Primary 9

  20. Channel Primary Secondary 9

  21. Timing 10

  22. Timing At-setup 10

  23. Timing At-setup On-demand 10

  24. k c a b d e e F implicit : sentiment analysis explicit : structured messages gathering users’ concerns 11

  25. Voicing User Concerns Providers traditionally say what they want 12

  26. Voicing User Concerns Providers Users’ concerns traditionally might not say what they be covered want 12

  27. Voicing User Concerns Providers Users’ concerns PriBots traditionally might not activate the say what they be covered two-way channel want 12

  28. 2- Setting Privacy Preferences 13

  29. 14

  30. Service and platform-dependent interface 14

  31. Service and platform-dependent interface Tradeo fg s for simplicity: try finding this setting on Mobile Web version 14

  32. 15

  33. Unique interface with all functionalities Ability to suggest adjustments to the user (combining notice and choice/preferences ) 15

  34. System Architecture User Analysis & Input Classification 16

  35. System Architecture Yes User Analysis & Structured Query Input Classification Query No Statement 16

  36. System Architecture Yes User Analysis & Structured Retrieval Query Result Input Classification Query Module No Statement Knowledge Base 16

  37. System Architecture Answer Yes Yes User Analysis & Structured Retrieval Query Confident? Result Formulation Input Classification Query Module in NL No Fallback Statement No Answer 
 Knowledge Generation Base 16

  38. System Architecture Answer Yes Yes User Analysis & Structured Retrieval Query Confident? Result Formulation Input Classification Query Module in NL No PriBot Fallback Statement No Reply Answer 
 Knowledge Generation Base 16

  39. System Architecture Answer Yes Yes User Analysis & Structured Retrieval Query Confident? Result Formulation Input Classification Query Module in NL No PriBot Fallback Statement No Reply Answer 
 Feedback Knowledge Feedback Generation DB Base DB Augment the Knowledge Base Amendments/ Analytics Improvements • unanswered queries • frequent questions • user sentiments 16

  40. Challenges 17

  41. Mature User Understanding Text processing Question answering Domain-specific datasets and ontologies Graceful fallback 18

  42. Legal Challenges Inherently error prone: are they legally binding? Accounting for false-positives and false-negatives The case of 3rd party PriBots: defamation possibilities? 19

  43. Trusting the Machine rule-based vs. AI-based user backlash? regulate the confidence level 20

  44. PriBots’ Personality positive tone → higher trust diversified content → reduced habituation 21

  45. t n e m y o l p e D 22

  46. t n e m y o l p e D provider 3rd parties 22

  47. t n e m y o l p e D provider 3rd parties Suitable for Voice Assistants 22

  48. What’s Next? Privacy as a Rule-based System User Dialogue Prototype Implementation studies 23

  49. Questions/Feedback? hamza.harkous@gmail.com hamzaharkous.com 24

  50. Image/Media Credits Zara Picken: slide 12 Egor Kosten: slide 24 Alex Prokhoda: slide 6 Freepik: slide 23 Geo fg Keough: slide 14 Victor: slide 12

Recommend

More recommend