Most current approaches for protecting privacy in machine learning (ML)
...
Neural language models are increasingly deployed into APIs and websites ...
Large language models are now tuned to align with the goals of their
cre...
We propose a scheme for auditing differentially private machine learning...
We propose a novel approach for developing privacy-preserving large-scal...
Model distillation is frequently proposed as a technique to reduce the
p...
In the privacy-utility tradeoff of a model trained on benchmark language...
Auditing mechanisms for differential privacy use probabilistic means to
...
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion ha...
Studying data memorization in neural language models helps us understand...
New methods designed to preserve data privacy require careful scrutiny.
...
Federated learning (FL) has emerged as an effective approach to address
...
Membership inference attacks are a key measure to evaluate privacy leaka...
Deep Neural Networks (DNNs) have become prevalent in wireless communicat...
Deep learning models leak significant amounts of information about their...
Deep Neural Networks (DNNs) are commonly used for various traffic analys...
Interactions between bids to show ads online can lead to an advertiser's...
Deep neural networks are susceptible to various inference attacks as the...
Flow correlation is the core technique used in a multitude of deanonymiz...
Machine learning models leak information about the datasets on which the...
A core technique used by popular proxy-based circumvention systems like ...