Privacy-preserving machine learning aims to train models on private data...
Motivated by recent developments in the shuffle model of differential
pr...
The ability to generate privacy-preserving synthetic versions of sensiti...
Auditing mechanisms for differential privacy use probabilistic means to
...
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion ha...
Differential Privacy (DP) provides a formal privacy guarantee preventing...
Given access to a machine learning model, can an adversary reconstruct t...
We study the difficulties in learning that arise from robust and
differe...
This paper aims to help structure the risk landscape associated with
lar...
Robustness of deep neural networks against adversarial perturbations is ...
Motivated by high-stakes decision-making domains like personalized medic...
Differentially Private Stochastic Gradient Descent (DP-SGD) forms a
fund...
The shuffle model of differential privacy (Erlingsson et al. SODA 2019; ...
Accurately learning from user data while providing quantifiable privacy
...
Reinforcement learning algorithms are known to be sample inefficient, an...
A protocol by Ishai et al. (FOCS 2006) showing how to implement distribu...
In recent work, Cheu et al. (Eurocrypt 2019) proposed a protocol for
n-p...
A fundamental result in differential privacy states that the privacy
gua...
Differential privacy is a mathematical framework for privacy-preserving ...
Differential privacy is the gold standard in data privacy, with applicat...
Active learning holds promise of significantly reducing data annotation ...
This work studies differential privacy in the context of the recently
pr...
Spectral methods of moments provide a powerful tool for learning the
par...
We study the problem of subsampling in differential privacy (DP), a ques...
Differential privacy comes equipped with multiple analytical tools for t...
The Gaussian mechanism is an essential building block used in multitude ...
We present the first differentially private algorithms for reinforcement...
This paper re-visits the spectral method for learning latent variable mo...