Machine Learning Security

Arjun Bahuguna (~arjun06)


Description:

Summary

With increased attack incidents on machine learning models (adversarial images, membership inference, model inversion, information reconstruction, data poisoning, etc) it becomes imperative for companies to be aware of the attack surface of their ML services and published results. The speakers will provide insights from their 3 years of research in privacy-preserving data mining, and show how companies like Google and Microsoft are coping with threats to their machine-learning models and user data privacy. The session will contain live-demos and be interactive.

Outcomes

  • Learn about attacks happening on ML models today
  • How to code defenses against them, using existing libraries

Prerequisites:

  1. Basic Linear Algebra

Content URLs:

https://docs.google.com/document/d/1fq5qLlG7mTOcNrr2amiSQh6KwtnUqNX7uRD5Q0p8QoU/edit?usp=sharing

Speaker Info:

Arjun Bahuguna is an applied cryptography researcher at Next Tech Lab, with a focus on privacy-enhancing technologies and machine learning security. In the last three years, his research has been awarded with two ACM grants, two university gold medals for original research, and multiple Innovation awards at International hackathons. He's also the organizer of PyData KTR and Papers We Love KTR.

Speaker Links:

  1. Twitter
  2. LinkedIn
  3. GitHub

Id: 1462
Section: Data Science, Machine Learning and AI
Type: Poster
Target Audience: Beginner
Last Updated: