January 15, 2020

188 words 1 min read

AI and security: Lessons, challenges, and future directions

AI and security: Lessons, challenges, and future directions

Dawn Song details challenges and exciting new opportunities at the intersection of AI and security and explains how AI and deep learning can enable better security and how security can enable better AI. You'll learn about secure deep learning and approaches to ensure the integrity of decisions made by deep learning.
Talk Title AI and security: Lessons, challenges, and future directions
Speakers Dawn Song (UC Berkeley)
Conference Artificial Intelligence Conference
Conf Tag Put AI to Work
Location San Francisco, California
Date September 5-7, 2018
URL Talk Page
Slides
Video Talk Video

Dawn Song details challenges and exciting new opportunities at the intersection of AI and security and explains how AI and deep learning can enable better security and how security can enable better AI. You’ll learn about secure deep learning and approaches to ensure the integrity of decisions made by deep learning. Dawn also offers an overview of the challenges of privacy-preserving machine learning and outlines new techniques to enable it. She then discusses a recent project on privacy-preserving smart contracts and working toward democratization of AI and shares future directions at the intersection of AI and security.

security smart contract ai privacy deep learning machine learning
comments powered by Disqus
Open source decentralized data markets for training AI in areas of large shared risk

Open source decentralized data markets for training AI in areas of large shared risk

January 11, 2020

Paco Nathan examines decentralized data markets. With components based on blockchain technologiessmart contracts, token-curated registries, DApps, voting mechanisms, etc.decentralized data markets allow multiple parties to curate ML training datasets in ways that are transparent, auditable, and secure and allow equitable payouts that take social values into account.
Machine Learning the Kubernetes Way

Machine Learning the Kubernetes Way

December 16, 2019

The Bloomberg Professional Service (aka "the Terminal") provides data, analytics, news, information and communication to professionals in business, finance, government, and philanthropy. Through our i …
Architecting an advanced analytics platform for machine learning

Architecting an advanced analytics platform for machine learning

November 18, 2019

Georgios Gkekas shares ING's advanced analytics journey to promote modern machine and deep learning techniques internally through a central, best-of-breed technical platform tailored for data science activities. The platform offers only the necessary automated tools to replace the tedious, repetitive, and error-prone steps in a typical data science pipeline.
AI for improving teaching and learning

AI for improving teaching and learning

January 15, 2020

We haven't figured out how to make the perfect robot tutors. But we have figured out how make them much more effective in improving student learning outcomes with modern AI techniques. Varun Arora covers some of those important techniques, along with real-world examples.
Deep learning for large-scale online fraud detection

Deep learning for large-scale online fraud detection

January 13, 2020

Online fraud is often orchestrated by organized crime rings, who use malicious user accounts to actively target modern online services for financial gain. Ting-Fang Yen shares a real-time, scalable fraud detection solution backed by deep learning and built on Spark and TensorFlow and demonstrates how the system outperforms traditional solutions such as blacklists and machine learning.
Executive Briefing: Best practices for human in the loopThe business case for active learning

Executive Briefing: Best practices for human in the loopThe business case for active learning

January 12, 2020

Deep learning works well when you have large labeled datasets, but not every team has those assets. Paco Nathan offers an overview of active learning, an ML variant that incorporates human-in-the-loop computing. Active learning focuses input from human experts, leveraging intelligence already in the system, and provides systematic ways to explore and exploit uncertainty in your data.