CourseClub Me Oreilly - Privacy-Preserving Machine Learning

1. 001. Part 1. Basics of privacy-preserving machine learning with differential privacy.mp42.34MB
2. 002. Chapter 1. Privacy considerations in machine learning.mp412.17MB
3. 003. Chapter 1. The threat of learning beyond the intended purpose.mp415.55MB
4. 004. Chapter 1. Threats and attacks for ML systems.mp434.41MB
5. 005. Chapter 1. Securing privacy while learning from data Privacy-preserving machine learning.mp428.85MB
6. 006. Chapter 1. How is this book structured.mp46.44MB
7. 007. Chapter 1. Summary.mp43.81MB
8. 008. Chapter 2. Differential privacy for machine learning.mp460.01MB
9. 009. Chapter 2. Mechanisms of differential privacy.mp452.83MB
10. 010. Chapter 2. Properties of differential privacy.mp447.45MB
11. 011. Chapter 2. Summary.mp45.1MB
12. 012. Chapter 3. Advanced concepts of differential privacy for machine learning.mp419.6MB
13. 013. Chapter 3. Differentially private supervised learning algorithms.mp447.46MB
14. 014. Chapter 3. Differentially private unsupervised learning algorithms.mp417.24MB
15. 015. Chapter 3. Case study Differentially private principal component analysis.mp464.12MB
16. 016. Chapter 3. Summary.mp44.54MB
17. 017. Part 2. Local differential privacy and synthetic data generation.mp41.14MB
18. 018. Chapter 4. Local differential privacy for machine learning.mp448.89MB
19. 019. Chapter 4. The mechanisms of local differential privacy.mp445.43MB
20. 020. Chapter 4. Summary.mp43.61MB
21. 021. Chapter 5. Advanced LDP mechanisms for machine learning.mp43.84MB
22. 022. Chapter 5. Advanced LDP mechanisms.mp425.93MB
23. 023. Chapter 5. A case study implementing LDP naive Bayes classification.mp453.74MB
24. 024. Chapter 5. Summary.mp42.49MB
25. 025. Chapter 6. Privacy-preserving synthetic data generation.mp418MB
26. 026. Chapter 6. Assuring privacy via data anonymization.mp415.08MB
27. 027. Chapter 6. DP for privacy-preserving synthetic data generation.mp428.43MB
28. 028. Chapter 6. Case study on private synthetic data release via feature-level micro-aggregation.mp444.93MB
29. 029. Chapter 6. Summary.mp42.83MB
30. 030. Part 3. Building privacy-assured machine learning applications.mp41.67MB
31. 031. Chapter 7. Privacy-preserving data mining techniques.mp49.68MB
32. 032. Chapter 7. Privacy protection in data processing and mining.mp48.09MB
33. 033. Chapter 7.3 Protecting privacy by modifying the input.mp44.36MB
34. 034. Chapter 7. Protecting privacy when publishing data.mp448.96MB
35. 035. Chapter 7. Summary.mp42.27MB
36. 036. Chapter 8. Privacy-preserving data management and operations.mp44.52MB
37. 037. Chapter 8. Privacy protection beyond k-anonymity.mp429.68MB
38. 038. Chapter 8. Protecting privacy by modifying the data mining output.mp413.89MB
39. 039. Chapter 8. Privacy protection in data management systems.mp480.56MB
40. 040. Chapter 8. Summary.mp43.63MB
41. 041. Chapter 9. Compressive privacy for machine learning.mp414.2MB
42. 042. Chapter 9. The mechanisms of compressive privacy.mp415.76MB
43. 043. Chapter 9. Using compressive privacy for ML applications.mp436.4MB
44. 044. Chapter 9. Case study Privacy-preserving PCA and DCA on horizontally partitioned data.mp4103.76MB
45. 045. Chapter 9. Summary.mp43.38MB
46. 046. Chapter 10. Putting it all together Designing a privacy-enhanced platform (DataHub).mp419.64MB
47. 047. Chapter 10. Understanding the research collaboration workspace.mp427.07MB
48. 048. Chapter 10. Integrating privacy and security technologies into DataHub.mp431.84MB
49. 049. Chapter 10. Summary.mp43.42MB