Characterizing the Space of Adversarial Examples in Machine Learning

Nicolas Papernot - PhD student, Computer Science and Engineering, Pennsylvania State University

Feb. 22, 2018, 10 a.m. - Feb. 22, 2018, 11 a.m.



There is growing recognition that machine learning (ML) exposes new security and privacy vulnerabilities in software systems, yet the technical community's understanding of the nature and extent of these vulnerabilities remains limited but expanding. In this talk, I explore the threat model space of ML algorithms, and systematically explore the vulnerabilities resulting from the poor generalization of ML models when they are presented with inputs manipulated by adversaries. This characterization of the threat space prompts an investigation of defenses that exploit the lack of reliable confidence estimates for predictions made. In particular, we introduce a promising new approach to defensive measures tailored to the structure of deep learning. Through this research, we expose connections between the resilience of ML to adversaries, model interpretability, and training data privacy.


Nicolas Papernot is a PhD student in Computer Science and Engineering working with Professor Patrick McDaniel at the Pennsylvania State University. His research interests lie at the intersection of computer security, privacy and machine learning. He is supported by a Google PhD Fellowship in Security and received a best paper award at ICLR 2017. He is also the co-author of CleverHans, an open-source library widely adopted in the technical community to benchmark machine learning in adversarial settings. In 2016, he received his M.S. in Computer Science and Engineering from the Pennsylvania State University and his M.S. in Engineering Sciences from the Ecole Centrale de Lyon.