research
∙
06/15/2023
ViP: A Differentially Private Foundation Model for Computer Vision
Artificial intelligence (AI) has seen a tremendous surge in capabilities...
share
research
∙
06/02/2023
Agnostic Multi-Group Active Learning
Inspired by the problem of improving classification accuracy on rare or ...
research
∙
05/18/2023
Data Redaction from Conditional Generative Models
Deep generative models are known to produce undesirable samples such as ...
research
∙
04/26/2023
Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning
Self-supervised learning (SSL) algorithms can produce useful image repre...
research
∙
03/07/2023
Can Membership Inferencing be Refuted?
Membership inference (MI) attack is currently the most popular test for ...
research
∙
02/25/2023
Data-Copying in Generative Models: A Formal Framework
There has been some recent interest in detecting and addressing memoriza...
research
∙
11/19/2022
A Two-Stage Active Learning Algorithm for k-Nearest Neighbors
We introduce a simple and intuitive two-stage active learning algorithm ...
research
∙
11/08/2022
The Interpolated MVU Mechanism For Communication-efficient Private Federated Learning
We consider private federated learning (FL), where a server aggregates d...
research
∙
10/25/2022
Robustness of Locally Differentially Private Graph Analysis Against Poisoning
Locally differentially private (LDP) graph analysis allows private analy...
research
∙
06/29/2022
Forgetting Data from Pre-trained GANs
Large pre-trained generative models are known to occasionally provide sa...
research
∙
06/17/2022
Thompson Sampling for Robust Transfer in Multi-Task Bandits
We study the problem of online multi-task learning where the tasks are p...
research
∙
06/09/2022
A Learning-Theoretic Framework for Certified Auditing of Machine Learning Models
Responsible use of machine learning requires that models be audited for ...
research
∙
05/23/2022
Throwing Away Data Improves Worst-Class Error in Imbalanced Classification
Class imbalances pervade classification problems, yet their treatment di...
research
∙
05/10/2022
Sentence-level Privacy for Document Embeddings
User language data can contain highly sensitive personal content. As suc...
research
∙
05/03/2022
Differentially Private Triangle and 4-Cycle Counting in the Shuffle Model
Subgraph counting is fundamental for analyzing connection patterns or cl...
research
∙
03/15/2022
Privacy-Aware Compression for Federated Data Analysis
Federated data analytics is a framework for distributed data analysis wh...
research
∙
02/10/2022
Understanding Rare Spurious Correlations in Neural Networks
Neural networks are known to use spurious correlations for classificatio...
research
∙
01/28/2022
Bounding Training Data Reconstruction in Private (Deep) Learning
Differential privacy is widely accepted as the de facto method for preve...
research
∙
01/13/2022
Privacy Amplification by Subsampling in Time Domain
Aggregate time-series data like traffic flow and site occupancy repeated...
research
∙
12/11/2021
Privacy Amplification via Shuffling for Linear Contextual Bandits
Contextual bandit algorithms are widely used in domains where it is desi...
research
∙
10/13/2021
Communication-Efficient Triangle Counting under Local Differential Privacy
Triangle counting in networks under LDP (Local Differential Privacy) is ...
research
∙
09/14/2021
Behavior of k-NN as an Instance-Based Explanation Method
Adoption of DL models in critical areas has led to an escalating demand ...
research
∙
06/11/2021
A Shuffling Framework for Local Differential Privacy
ldp deployments are vulnerable to inference attacks as an adversary can ...
research
∙
05/29/2021
Understanding Instance-based Interpretability of Variational Auto-Encoders
Instance-based interpretation methods have been widely studied for super...
research
∙
05/21/2021
Privacy Amplification Via Bernoulli Sampling
Balancing privacy and accuracy is a major challenge in designing differe...
research
∙
03/10/2021
Universal Approximation of Residual Flows in Maximum Mean Discrepancy
Normalizing flows are a class of flexible deep generative models that of...
research
∙
02/18/2021
Consistent Non-Parametric Methods for Adaptive Robustness
Learning classifiers that are robust to adversarial examples has receive...
research
∙
02/14/2021
Connecting Interpretability and Robustness in Decision Trees through Separation
Recent research has recognized interpretability and robustness as essent...
research
∙
12/19/2020
Sample Complexity of Adversarially Robust Linear Classification on Separated Data
We consider the sample complexity of learning with adversarial robustnes...
research
∙
11/17/2020
Close Category Generalization
Out-of-distribution generalization is a core challenge in machine learni...
research
∙
11/06/2020
Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning
The Private Aggregation of Teacher Ensembles (PATE) framework is one of ...
research
∙
10/29/2020
Multitask Bandit Learning through Heterogeneous Feedback Aggregation
In many real-world applications, multiple agents seek to learn how to pe...
research
∙
10/17/2020
Locally Differentially Private Analysis of Graph Statistics
Differentially private analysis of graphs is widely used for releasing s...
research
∙
08/10/2020
Trustworthy AI Inference Systems: An Industry Research View
In this work, we provide an industry research view for approaching the d...
research
∙
05/31/2020
The Expressive Power of a Class of Normalizing Flow Models
Normalizing flows have received a great deal of recent attention as they...
research
∙
05/24/2020
Successive Refinement of Privacy
This work examines a novel question: how much randomness is needed to ac...
research
∙
04/12/2020
A Non-Parametric Test to Detect Data-Copying in Generative Models
Detecting overfitting in generative models is an important challenge in ...
research
∙
03/13/2020
When are Non-Parametric Methods Robust?
A growing body of research has shown that many classifiers are susceptib...
research
∙
02/24/2020
Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluations
Deleting data from a trained machine learning (ML) model is a critical t...
research
∙
12/09/2019
Location Trace Privacy Under Conditional Priors
Providing meaningful privacy to users of location based services is part...
research
∙
07/03/2019
Capacity Bounded Differential Privacy
Differential privacy, a notion of algorithmic stability, is a gold stand...
research
∙
06/07/2019
Adversarial Examples for Non-Parametric Methods: Attacks, Defenses and Large Sample Limits
Adversarial examples have received a great deal of recent attention beca...
research
∙
05/29/2019
The Label Complexity of Active Learning from Observational Data
Counterfactual learning from observational data involves learning a clas...
research
∙
05/28/2019
An Investigation of Data Poisoning Defenses for Online Learning
We consider data poisoning attacks, where an adversary can modify a smal...
research
∙
11/05/2018
Model Extraction and Active Learning
Machine learning is being increasingly used by individuals, research ins...
research
∙
09/12/2018
The Inductive Bias of Restricted f-GANs
Generative adversarial networks are a novel method for statistical infer...
research
∙
09/07/2018
Differentially Private Continual Release of Graph Statistics
Motivated by understanding the dynamics of sensitive social networks ove...
research
∙
08/27/2018
Data Poisoning Attacks against Online Learning
We consider data poisoning attacks, a class of adversarial attacks on ma...
research
∙
02/25/2018
Active Learning with Logged Data
We consider active learning with logged data, where labeled examples are...
research
∙
02/07/2018