37 citations · 63 across the 25 of their papers we have counts for
9 papers · 1 filter
Inadvertent Context Leakage in Language Models
Jaiden Fairoze, Neal Mangaokar, Kamalika Chaudhuri +2
For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data. We study whether the mere p…
Privacy Blur: Quantifying Privacy and Utility for Image Data Release
Saeed Mahloujifar, Narine Kokhlikyan, Chuan Guo +1
Image data collected in the wild often contains private information such as faces and license plates, and responsible data release must ensure that this information stays hidden. A…
Z0-Inf: Zeroth Order Approximation for Data Influence
Narine Kokhlikyan, Kamalika Chaudhuri, Saeed Mahloujifar
A critical aspect of analyzing and improving modern machine learning systems lies in understanding how individual training examples influence a model's predictive behavior. Estimat…
Measuring Déjà vu Memorization Efficiently
Narine Kokhlikyan, Bargav Jayaraman, Florian Bordes +2
Recent research has shown that representation learning models may accidentally memorize their training data. For example, the déjà vu method shows that for certain representation l…
Auditing -Differential Privacy in One Run
Saeed Mahloujifar, Luca Melis, Kamalika Chaudhuri
Empirical auditing has emerged as a means of catching some of the flaws in the implementation of privacy-preserving algorithms. Existing auditing mechanisms, however, are either co…
An Introduction to Vision-Language Modeling
Florian Bordes, Richard Yuanzhe Pang, Anurag Ajay +38
Following the recent popularity of Large Language Models (LLMs), several attempts have been made to extend them to the visual domain. From having a visual assistant that could guid…
Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds
Kamalika Chaudhuri, Chuan Guo, Laurens van der Maaten +2
Protecting privacy during inference with deep neural networks is possible by adding noise to the activations in the last layers prior to the final classifiers or other task-specifi…
DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
Jonathan Lebensold, Maziar Sanjabi, Pietro Astolfi +4
Text-to-image diffusion models have been shown to suffer from sample-level memorization, possibly reproducing near-perfect replica of images that they are trained on, which may be…
Differentially Private Multi-Site Treatment Effect Estimation
Tatsuki Koga, Kamalika Chaudhuri, David Page
Patient privacy is a major barrier to healthcare AI. For confidentiality reasons, most patient data remains in silo in separate hospitals, preventing the design of data-driven heal…