Yimin Chen, "Delving into differential privacy and anomaly detection: a meta-learning perspective"
CERIAS Weekly Security Seminar - Purdue University
English - April 14, 2021 20:30 - 402 MB Video - ★★★★ - 6 ratingsTechnology Education Courses infosec security video seminar cerias purdue information sfs research education Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
In this talk, we explore security and privacy related to
meta-learning, a learning paradigm aiming to learn 'cross-task'
knowledge instead of 'single-task' knowledge. For privacy
perspective, we conjecture that meta-learning plays an important
role in future federated learning and look into federated
meta-learning systems with differential privacy design for task
privacy protection. For security perspective, we explore anomaly
detection for machine learning models. Particularly, we explore
poisoning attacks on machine learning models in which poisoning
training samples are the anomaly. Inspired from that poisoning
samples degrade trained models through overfitting, we exploit
meta-training to counteract overfitting, thus enhancing model
robustness.