542 citations · 1.6k across the 85 of their papers we have counts for
91 papers
Metric Differential Privacy at the User-Level Via the Earth Mover's Distance
Jacob Imola, Amrita Roy Chowdhury, Kamalika Chaudhuri
Metric differential privacy (DP) provides heterogeneous privacy guarantees based on a distance between the pair of inputs. It is a widely popular notion of privacy since it capture…
FairProof : Confidential and Certifiable Fairness for Neural Networks
Chhavi Yadav, Amrita Roy Chowdhury, Dan Boneh +1
Machine learning models are increasingly used in societal applications, yet legal and privacy concerns demand that they very often be kept confidential. Consequently, there is a gr…
Large-Scale Public Data Improves Differentially Private Image Generation Quality
Ruihan Wu, Chuan Guo, Kamalika Chaudhuri
Public data has been frequently used to improve the privacy-accuracy trade-off of differentially private machine learning, but prior work largely assumes that this data come from t…
ViP: A Differentially Private Foundation Model for Computer Vision
Yaodong Yu, Maziar Sanjabi, Yi Ma +2
Artificial intelligence (AI) has seen a tremendous surge in capabilities thanks to the use of foundation models trained on internet-scale data. On the flip side, the uncurated natu…
Agnostic Multi-Group Active Learning
Nick Rittler, Kamalika Chaudhuri
Inspired by the problem of improving classification accuracy on rare or hard subsets of a population, there has been recent interest in models of learning where the goal is to gene…
Data Redaction from Conditional Generative Models
Zhifeng Kong, Kamalika Chaudhuri
Deep generative models are known to produce undesirable samples such as harmful content. Traditional mitigation methods include re-training from scratch, filtering, or editing; how…
Pool Inference Attacks on Local Differential Privacy: Quantifying the Privacy Guarantees of Apple's Count Mean Sketch in Practice
Andrea Gadotti, Florimond Houssiau, Meenatchi Sundaram Muthu Selva Annamalai +1
Behavioral data generated by users' devices, ranging from emoji use to pages visited, are collected at scale to improve apps and services. These data, however, contain fine-grained…
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…
Can Membership Inferencing be Refuted?
Zhifeng Kong, Amrita Roy Chowdhury, Kamalika Chaudhuri
Membership inference (MI) attack is currently the most popular test for measuring privacy leakage in machine learning models. Given a machine learning model, a data point and some…
Data-Copying in Generative Models: A Formal Framework
Robi Bhattacharjee, Sanjoy Dasgupta, Kamalika Chaudhuri
There has been some recent interest in detecting and addressing memorization of training data by deep neural networks. A formal framework for memorization in generative models, cal…
A Two-Stage Active Learning Algorithm for -Nearest Neighbors
Nick Rittler, Kamalika Chaudhuri
-nearest neighbor classification is a popular non-parametric method because of desirable properties like automatic adaption to distributional scale changes. Unfortunately, it ha…
Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design
Chuan Guo, Kamalika Chaudhuri, Pierre Stock +1
In private federated learning (FL), a server aggregates differentially private updates from a large number of clients in order to train a machine learning model. The main challenge…
Robustness of Locally Differentially Private Graph Analysis Against Poisoning
Jacob Imola, Amrita Roy Chowdhury, Kamalika Chaudhuri
Locally differentially private (LDP) graph analysis allows private analysis on a graph that is distributed across multiple users. However, such computations are vulnerable to data…
Robust Empirical Risk Minimization with Tolerance
Robi Bhattacharjee, Max Hopkins, Akash Kumar +2
Developing simple, sample-efficient learning algorithms for robust classification is a pressing issue in today's tech-dominated world, and current theoretical techniques requiring…
Thompson Sampling for Robust Transfer in Multi-Task Bandits
Zhi Wang, Chicheng Zhang, Kamalika Chaudhuri
We study the problem of online multi-task learning where the tasks are performed within similar but not necessarily identical multi-armed bandit environments. In particular, we stu…
Data Redaction from Pre-trained GANs
Zhifeng Kong, Kamalika Chaudhuri
Large pre-trained generative models are known to occasionally output undesirable samples, which undermines their trustworthiness. The common way to mitigate this is to re-train the…
XAudit : A Theoretical Look at Auditing with Explanations
Chhavi Yadav, Michal Moshkovitz, Kamalika Chaudhuri
Responsible use of machine learning requires models to be audited for undesirable properties. While a body of work has proposed using explanations for auditing, how to do so and wh…
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…
Why does Throwing Away Data Improve Worst-Group Error?
Kamalika Chaudhuri, Kartik Ahuja, Martin Arjovsky +1
When facing data with imbalanced classes or groups, practitioners follow an intriguing strategy to achieve best results. They throw away examples until the classes or groups are ba…
Differentially Private Triangle and 4-Cycle Counting in the Shuffle Model
Jacob Imola, Takao Murakami, Kamalika Chaudhuri
Subgraph counting is fundamental for analyzing connection patterns or clustering tendencies in graph data. Recent studies have applied LDP (Local Differential Privacy) to subgraph…
Privacy-Aware Compression for Federated Data Analysis
Kamalika Chaudhuri, Chuan Guo, Mike Rabbat
Federated data analytics is a framework for distributed data analysis where a server compiles noisy responses from a group of distributed low-bandwidth user devices to estimate agg…
Understanding Rare Spurious Correlations in Neural Networks
Yao-Yuan Yang, Chi-Ning Chou, Kamalika Chaudhuri
Neural networks are known to use spurious correlations such as background information for classification. While prior work has looked at spurious correlations that are widespread i…
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…
Bounding Training Data Reconstruction in Private (Deep) Learning
Chuan Guo, Brian Karrer, Kamalika Chaudhuri +1
Differential privacy is widely accepted as the de facto method for preventing data leakage in ML, and conventional wisdom suggests that it offers strong protection against privacy…