log in  |  register  |  feedback?  |  help  |  web accessibility
Logo
SoK: Security and Privacy in Machine Learning
Neal Gupta - UMD
Friday, October 12, 2018, 11:00 am-12:00 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)
Abstract

In this talk, Neal Gupta will present us an SoK paper on adversarial machine learning (AML). The paper SoK: Security and Privacy in Machine Learning, by Papernot et al. is presented in Euro S&P2018, and it constitutes a great overview of the research in AML and provides a categorization of the attacks and defenses proposed so far. Adversarial machine learning is an emerging hot topic and I would recommend everyone to attend to the talk. Lunch will be provided.

 

Advances in machine learning (ML) in recent years have enabled a dizzying array of applications such as data analytics, autonomous systems, and security diagnostics. ML is now pervasive—new systems and models are being deployed in every domain imaginable, leading to widespread deployment of software based inference and decision making. There is growing recognition that ML exposes new vulnerabilities in software systems, yet the technical community’s understanding of the nature and extent of these vulnerabilities remains limited. We systematize findings on ML security and privacy, focusing on attacks identified on these systems and defenses crafted to date. We articulate a comprehensive threat model for ML, and categorize attacks and defenses within an adversarial framework. Key insights resulting from works both in the ML and security communities are identified and the effectiveness of approaches are related to structural elements of ML algorithms and the data used to train them. In particular, it is apparent that constructing a theoretical understanding of the sensitivity of modern ML algorithms to the data they analyze, a la PAC theory, will foster a science of security and privacy in ML.

Bio

Neal Gupta is a PhD student in Computer Science. From 2011-12 he was a Master's student in Economics at the London School of Economics, and he has an undergraduate degree in Applied Mathematics from Harvard College. His research interests include mathematical network analysis, applied mathematical optimization, and automated planning.

This talk is organized by Yigitcan Kaya