Presented By
O’Reilly + Cloudera
Make Data Work
March 25-28, 2019
San Francisco, CA

AI privacy and ethical compliance toolkit

Iman Saleh (Intel), Cory Ilo (Intel), Cindy Tseng (Intel)
9:00am12:30pm Tuesday, March 26, 2019
Secondary topics:  Ethics, Security and Privacy
Average rating: *****
(5.00, 3 ratings)

Who is this presentation for?

  • Developers, data scientists, and solutions architects

Level

Intermediate

Prerequisite knowledge

  • A basic understanding of machine learning and deep learning
  • A working knowledge of Python

Materials or downloads needed in advance

  • A laptop with the Python interpreter installed

What you'll learn

  • Learn best practices for ensuring fairness and privacy compliance for machine learning applications
  • Explore tools that data scientists can use to ensure privacy and fairness of their models
  • Understand privacy by design concepts

Description

New applications of machine learning are raising ethical concerns about a host of issues, including bias, transparency, and privacy. Iman Saleh, Cory Ilo, and Cindy Tseng demonstrate tools and capabilities that can help data scientists address these concerns and bridge the gap between ethicists, regulators, and machine learning practitioners.

Topics include:

  • Privacy-preserving face landmarks detection: Learn how to design for privacy preservation in a face detection framework. This design approach enables the extraction of facial features and does not compromise the user’s identity.
  • Vehicle data assurance (VEDA): Autonomous vehicles are characterized by the collection of huge amount of sensor data used to train ML models. Explore a solution, VEDA, to ensure compliance with strict privacy regulations regarding the use and handling of this data and to increase trust in the collected data and its management lifecycle.
  • Bias detection and remediation: Computer vision algorithms can be biased to certain ages, races, or genders based on the training datasets. Discover how to detect these biases and how tools can be used to rebalance a biased dataset.
Photo of Iman Saleh

Iman Saleh

Intel

Iman Saleh is a research scientist with the Automotive Solutions Group at Intel. Iman has authored 30+ technical publications in the areas of big data, formal data specification, service-oriented computing, and privacy-preserving data mining. Her research interests include ethical AI, machine learning, privacy-preserving solutions, software engineering, data modeling, web services, formal methods, and cryptography. She holds a PhD from the Computer Science Department at Virginia Tech, a master’s degree in computer science from Alexandria University, Egypt, and a master’s degree in software engineering from Virginia Tech.

Photo of Cory Ilo

Cory Ilo

Intel

Cory Ilo is a computer vision engineer in the Automotive Solutions Group at Intel, where he helps prototype and research the feasibility of various computer vision solutions in relation to privacy, ethics, deep learning, and autonomous vehicles. In his spare time, Cory focuses on his passion for fitness, video games, and wanderlust, in addition to finding ways on how they tie into computer vision.

Photo of Cindy Tseng

Cindy Tseng

Intel

Cindy Tseng is a research scientist with the Applied Research in Automotive Driving Group at Intel, where she has recently been focusing on bias detection in convolution neural nets. Cindy has also worked in the high-throughput computing and deep learning hardware accelerator spaces. She holds a master’s degree from the Electrical and Computer Engineering Department at Carnegie Mellon University and a bachelor’s degree in electrical engineering and computer science from the University of Michigan-Ann Arbor. Cindy is currently enrolled as a part-time student in the Masters in Data Science Program in Computer Science at the University of Illinois Urbana-Champaign.