research
∙
08/21/2023
Unlocking Accuracy and Fairness in Differentially Private Image Classification
Privacy-preserving machine learning aims to train models on private data...
share
research
∙
07/08/2023
Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy
We explore Reconstruction Robustness (ReRo), which was recently proposed...
research
∙
02/27/2023
Differentially Private Diffusion Models Generate Useful Synthetic Images
The ability to generate privacy-preserving synthetic versions of sensiti...
research
∙
02/15/2023
Tight Auditing of Differentially Private Machine Learning
Auditing mechanisms for differential privacy use probabilistic means to ...
research
∙
01/30/2023
Extracting Training Data from Diffusion Models
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion ha...
research
∙
04/28/2022
Unlocking High-Accuracy Differentially Private Image Classification through Scale
Differential Privacy (DP) provides a formal privacy guarantee preventing...
research
∙
01/13/2022
Reconstructing Training Data with Informed Adversaries
Given access to a machine learning model, can an adversary reconstruct t...
research
∙
01/06/2022
Learning to be adversarially robust and differentially private
We study the difficulties in learning that arise from robust and differe...
research
∙
11/14/2020
Towards transformation-resilient provenance detection of digital media
Advancements in deep generative models have made it possible to synthesi...
research
∙
10/19/2020
Adaptive Traffic Fingerprinting: Large-scale Inference under Realistic Assumptions
The widespread adoption of encrypted communications (e.g., the TLS proto...
research
∙
09/08/2020
Toward Robustness and Privacy in Federated Learning: Experimenting with Local and Central Differential Privacy
Federated Learning (FL) allows multiple participants to collaboratively ...
research
∙
06/08/2020
Provable trade-offs between private robust machine learning
Historically, machine learning methods have not been designed with secur...
research
∙
06/07/2020
Extensions and limitations of randomized smoothing for robustness guarantees
Randomized smoothing, a method to certify a classifier's decision on an ...
research
∙
06/06/2020
Unique properties of adversarially trained linear classifiers on Gaussian data
Machine learning models are vulnerable to adversarial perturbations, tha...
research
∙
01/08/2019
Contamination Attacks and Mitigation in Multi-Party Machine Learning
Machine learning is data hungry; the more data a model has access to in ...
research
∙
11/15/2018
A note on hyperparameters in black-box adversarial examples
Since Biggio et al. (2013) and Szegedy et al. (2013) first drew attentio...
research
∙
10/25/2018
Evading classifiers in discrete domains with provable optimality guarantees
Security-critical applications such as malware, fraud, or spam detection...
research
∙
08/17/2017
Machine Learning as an Adversarial Service: Learning Black-Box Adversarial Examples
Neural networks are known to be vulnerable to adversarial examples, inpu...
research
∙
03/01/2017