Title: Towards Resilient Machine Learning in Adversarial Environments
Machine learning is increasingly being used for automated decisions in applications such as health care, finance, and cyber security. In these critical environments, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms. The area of adversarial machine learning studies the effect of adversarial attacks against machine learning models and aims to design robust defense algorithms. In this talk I will first describe several applications of machine learning for advanced threat detection. Then, I will present recent work on poisoning attacks at training time and evasion attacks at testing time against different classification and regression algorithms. I will discuss the impact of the attacks on several real-world applications from cyber security and self-driving cars. I will also mention a number of challenges in securing machine learning in critical adversarial environments.
About the speaker:
Alina Oprea is an Associate Professor at Northeastern University in the Khoury College of Computer Sciences. She joined Northeastern University in Fall 2016 after spending 9 years as a research scientist at RSA Laboratories. Her research interests are broadly in cyber security, with a focus on adversarial machine learning, security analytics, cloud security, and applied cryptography. She is the recipient of the Technology Review TR35 award for research in cloud security in 2011 and the recipient of the Google Security and Privacy Award in 2019. Alina serves currently as Program Committee co-chair of the IEEE Security and Privacy Symposium, 2020, and as Associate Editor of the ACM Transactions of Privacy and Security (TOPS) journal.
Host: David Evans