Adversarial Machine Learning: Categories, Concepts, and Current Landscape
Offered By: Inside Livermore Lab via YouTube
Course Description
Overview
Explore the critical vulnerabilities in machine learning systems through this comprehensive seminar on adversarial machine learning. Delve into the three main categories of algorithmic vulnerabilities that can be exploited even when hardware, software, and network environments are secure. Understand how adversaries can manipulate training data, alter test data to evade correct outcomes, and extract sensitive information from models. Gain insights into the importance of developing a robust adversarial model when conducting or utilizing adversarial machine learning research. Examine recent academic work in the field, focusing on unique cases that challenge traditional categorizations. Learn from Philip Kegelmeyer, a Senior Scientist at SNL Livermore, as he shares his expertise in counter adversarial data analytics and supervised machine learning algorithms.
Syllabus
DSI | Adversarial Machine Learning: Categories, Concepts, and Current Landscape
Taught by
Inside Livermore Lab
Related Courses
Excel 2010Miríadax Intro to Data Science
Udacity Data Manipulation at Scale: Systems and Algorithms
University of Washington via Coursera Statistical Computing with R - a gentle introduction
University College London via Independent Introducción a Data Science: Programación Estadística con R
Universidad Nacional Autónoma de México via Coursera