The focus of the Center is to develop a rigorous understanding of the vulnerabilities inherent to machine learning, and to develop the tools, metrics, and methods to mitigate them.
Background. Recent advances in machine learning (ML) have vastly improved computational reasoning over complex domains. From video and text classification, to complex data analysis, machine learning is constantly finding new applications. Yet, when machine learning models are exposed to adversarial behavior, the systems built upon them can be fooled, evaded, and misled in ways that can have profound security implications. As more critical systems employ ML—from financial systems to self-driving cars to network monitoring tools—it is vitally important that we develop the rigorous scientific techniques needed to make machine learning more robust to attack. This nascent field, which we call trustworthy machine learning, is currently fragmented across several research communities including machine learning, security, statistics, and theoretical computer science.
NEWS AT CTML
Penn State’s Computer Science and Engineering Camp for Girls
Students in 7th to 12th grade are invited to Dancing with Robots. They will gain experience and excitement through first-hand interactions with artificial beings in the real, virtual, and augmented reality worlds.
CTML First Internal Assessment
To review our first year’s progress towards our stated Y1 goals; specifically:
- developing formal definitions & theory for robustness
- continuing ongoing formal & empirical studies of inference & training time attacks
- developing initial evaluation environment
NSF SaTC PI meeting
Fourth biennial NSF Secure and Trustworthy Cyberspace (SaTC) Principal Investigators’ Meetin, focused this year on Growing the Cybersecurity Research Pipeline: how can SaTC involve more undergraduates in research, and inspire them to pursue graduate studies in cybersecurity? How can SaTC increase diversity and inclusivity in cybersecurity research?