CIS Seminar: “Privacy, Copyright, and Data Integrity: The Cascading Implications of Generative AI”
The rapid adoption of generative AI has created a cycle where personal information cascades perpetually: from people to models to applications and online platforms, then back through scrapers into the […]
CIS Seminar: “Realizing the Promise of Language-level Security in Real Systems”
Promises are cheap. Software vendors routinely describe their offerings as “secure”, but few are based on designs that can guarantee even the most basic security properties. To address this problem, […]
CIS Seminar: “Learning Theoretic Foundations for Modern (Data) Science”
In this talk, I will explain how fundamental problems in computational learning theory are at the heart of modern problems in machine learning and scientific applications and how algorithmic insights […]
ESE Guest Seminar – “On Team Decision Problems with Nonclassical Information Structures”
Team theory is a mathematical formalism for decentralized stochastic control problems in which a “team,” consisting of a number of members, cooperates to achieve a common objective. It was developed […]
CIS Seminar: ” Specializing LLMs for Reliability”
Large language models (LLMs) have advanced the frontiers of AI reasoning: they can synthesize information from multiple sources, derive new conclusions, and explain those conclusions to their users. However, LLMs […]
CIS Seminar: “Efficient Probabilistically Checkable Proofs from High-Dimensional Expanders”
The PCP theorem, proved in the 90’s, shows how to encode a proof for any theorem into a format where the theorem’s correctness can be verified by making only a […]
CIS Seminar: “Bridging Informal and Formal AI Reasoning”
Neural language models have opened a fascinating, flexible platform for reasoning in mathematics, programming, and beyond. This talk will explore the intersection of these models and the rigor of formal […]
ASSET Seminar: “Algorithmic Stability for Trustworthy Machine Learning and Statistics”
Abstract: Data-driven systems hold immense potential to positively impact society, but their reliability remains a challenge. Their outputs are often too brittle to changes in their training data, leaving them […]
CIS Seminar: “Leveraging the Wisdom of Clouds for Internet Security”
Over the past decade, networked systems have consolidated under just a handful of hyperscale cloud providers (e.g., AWS, Azure). While this offers logistical and economic advantages, attackers specifically target providers […]
IDEAS/STAT Optimization Seminar: “Negative Stepsizes Make Gradient-Descent-Ascent Converge”
Zoom link: https://upenn.zoom.us/j/98220304722 Abstract: Solving min-max problems is a central question in optimization, games, learning, and controls. Arguably the most natural algorithm is Gradient-Descent-Ascent (GDA), however since the 1970s, conventional wisdom […]