16 citations · 22 across the 10 of their papers we have counts for
11 papers
Exploring The Empirical Privacy Landscape of Synthetic Data
Zihao Zhao, Avi Schwarzschild, Casey Meehan +3
Methods for training language models on sensitive data differ in how they balance capability gains against the risk of leaking private information. In this paper, we present a cont…
Model Card for OpenAI Privacy Filter
Charles de Bourcy, Sahra Ghalebikesabi, Avi Schwarzschild +22
OpenAI Privacy Filter is a compact, bidirectional token-classification model for detecting and redacting personally identifiable information (PII) and secrets in unstructured text.…
Measuring Privacy Loss in Distributed Spatio-Temporal Data
Tatsuki Koga, Casey Meehan, Kamalika Chaudhuri
Statistics about traffic flow and people's movement gathered from multiple geographical locations in a distributed manner are the driving force powering many applications, such as…
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
Anvith Thudi, Hengrui Jia, Casey Meehan +2
Differentially private stochastic gradient descent (DP-SGD) is the canonical approach to private deep learning. While the current privacy analysis of DP-SGD is known to be tight in…
Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning
Casey Meehan, Florian Bordes, Pascal Vincent +2
Self-supervised learning (SSL) algorithms can produce useful image representations by learning to associate different parts of natural images with one another. However, when taken…
Sentence-level Privacy for Document Embeddings
Casey Meehan, Khalil Mrini, Kamalika Chaudhuri
User language data can contain highly sensitive personal content. As such, it is imperative to offer users a strong and interpretable privacy guarantee when learning from their dat…
Privacy Amplification by Subsampling in Time Domain
Tatsuki Koga, Casey Meehan, Kamalika Chaudhuri
Aggregate time-series data like traffic flow and site occupancy repeatedly sample statistics from a population across time. Such data can be profoundly useful for understanding tre…
A Shuffling Framework for Local Differential Privacy
Casey Meehan, Amrita Roy Chowdhury, Kamalika Chaudhuri +1
ldp deployments are vulnerable to inference attacks as an adversary can link the noisy responses to their identity and subsequently, auxiliary information using the order of the da…
Location Trace Privacy Under Conditional Priors
Casey Meehan, Kamalika Chaudhuri
Providing meaningful privacy to users of location based services is particularly challenging when multiple locations are revealed in a short period of time. This is primarily due t…
A Non-Parametric Test to Detect Data-Copying in Generative Models
Casey Meehan, Kamalika Chaudhuri, Sanjoy Dasgupta
Detecting overfitting in generative models is an important challenge in machine learning. In this work, we formalize a form of overfitting that we call {\em{data-copying}} -- where…
Location Trace Privacy Under Conditional Priors
Casey Meehan, Kamalika Chaudhuri
Providing meaningful privacy to users of location based services is particularly challenging when multiple locations are revealed in a short period of time. This is primarily due t…