Adversarial and Poisoning Attacks Against Speech Systems - Where to Find Them
Offered By: Center for Language & Speech Processing(CLSP), JHU via YouTube
Course Description
Overview
Explore the intricate world of machine learning system vulnerabilities in this 38-minute presentation by research scientist Thomas Thebuad from the Center for Language & Speech Processing at JHU. Delve into poisoning attacks and their impact on data integrity, understanding how malicious alterations can affect machine learning outcomes. Learn about "dirty labels" and "clean label" poisoning, and discover the dangers of adversarial attacks that can deceive models into incorrect predictions. Gain insights into the complex interactions between training data and system performance, emphasizing the importance of trust in data integrity. Examine real-world examples and theoretical concepts to understand various attack strategies, defense mechanisms, and the ongoing battle between system security and adversarial tactics. Equip yourself with a deeper understanding of the challenges and necessary precautions in developing robust machine learning systems, whether you're a cybersecurity expert, machine learning enthusiast, or interested in the ethical implications of AI.
Syllabus
Adversarial and Poisoning Attacks against Speech Systems: Where to Find Them?
Taught by
Center for Language & Speech Processing(CLSP), JHU
Related Courses
Introduction to Artificial IntelligenceStanford University via Udacity Natural Language Processing
Columbia University via Coursera Probabilistic Graphical Models 1: Representation
Stanford University via Coursera Computer Vision: The Fundamentals
University of California, Berkeley via Coursera Learning from Data (Introductory Machine Learning course)
California Institute of Technology via Independent