Publications (10)
Provably Robust Watermarks for Open-Source Language Models
Miranda Christ, Sam Gunn, Tal Malkin +1
The recent explosion of high-quality language models has necessitated new methods for identifying AI-generated text. Watermarking is a leading solution and could prove to be an ess…
Certification of Machine Learning Models via Directional Sharpness
Gefei Tan, Adria Gascon, Sarah Meiklejohn +1
In machine learning, model certification has been identified as an important method for gaining assurance about a model's trustworthiness and quality. A model's quality is largely…
Engineering Robustness into Personal Agents with the AI Workflow Store
Roxana Geambasu, Mariana Raykova, Pierre Tholoniat +3
The dominant paradigm for AI agents is an "on-the-fly" loop in which agents synthesize plans and execute actions within seconds or minutes in response to user prompts. We argue tha…
A Risk Assessment Framework for Digital Identification Systems
Allison Woodruff, Dirk Balfanz, Will Drewry +1
We introduce a risk assessment framework for digital identification systems, as well as recommended best practices to enhance privacy, security, and other desirable properties in t…
Secure Computation for Machine Learning With SPDZ
Valerie Chen, Valerio Pastro, Mariana Raykova
Secure Multi-Party Computation (MPC) is an area of cryptography that enables computation on sensitive data from multiple sources while maintaining privacy guarantees. However, theo…
Advances and Open Problems in Federated Learning
Peter Kairouz, H. Brendan McMahan, Brendan Avent +56
Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a cen…
Think Global, Act Local: Gossip and Client Audits in Verifiable Data Structures
Sarah Meiklejohn, Pavel Kalinnikov, Cindy S. Lin +4
In recent years, there has been increasing recognition of the benefits of having services provide auditable logs of data, as demonstrated by the deployment of Certificate Transpare…
UN Handbook on Privacy-Preserving Computation Techniques
David W. Archer, Borja de Balle Pigem, Dan Bogdanov +10
This paper describes privacy-preserving approaches for the statistical analysis. It describes motivations for privacy-preserving approaches for the statistical analysis of sensitiv…
On the Differential Privacy and Interactivity of Privacy Sandbox Reports
Badih Ghazi, Charlie Harrison, Arpana Hosabettu +8
The Privacy Sandbox initiative from Google includes APIs for enabling privacy-preserving advertising functionalities as part of the effort around limiting third-party cookies. In p…
Differentially Private Ad Conversion Measurement
John Delaney, Badih Ghazi, Charlie Harrison +6
In this work, we study ad conversion measurement, a central functionality in digital advertising, where an advertiser seeks to estimate advertiser website (or mobile app) conversio…