Presentation: AI & Security: Lessons and Challenges
Abstract
In this talk, I will first present recent results in the area of secure deep learning, in particular, adversarial deep learning---how deep learning systems could be easily fooled and what we need to do to address the issues. I will also talk about how AI and deep learning can help enable new capabilities in security applications. Finally, I will conclude with key challenges and future directions at the intersection of AI and Security: how AI and deep learning can enable better security, and how Security can enable better AI.
Similar Talks
Machine Learning on Mobile and Edge Devices With TensorFlow Lite
Developer Advocate for TensorFlow Lite @Google and Co-Author of TinyML
Daniel Situnayake
Self-Driving Cars as Edge Computing Devices
Sr. Staff Engineer @UberATG
Matt Ranney
License Compliance for Your Container Supply Chain
Open Source Engineer @VMware
Nisha Kumar
Exploiting Common iOS Apps’ Vulnerabilities
Software Engineer @Google
Ivan Rodriguez
Securing Software From the Supply Side
Senior Engineering Manager @GitHub
Nickolas Means
CI/CD for Machine Learning
Program Manager on the Azure DevOps Engineering Team @Microsoft
Sasha Rosenbaum
ML's Hidden Tasks: A Checklist for Developers When Building ML Systems
Senior Machine Learning Engineer @teamretrorabbit
Jade Abbott
From POC to Production in Minimal Time - Avoiding Pain in ML Projects
Chief Science Officer @StoryStreamAI
Janet Bastiman
ML in the Browser: Interactive Experiences with Tensorflow.js
Research Engineer in Machine Learning @cloudera