95 citations · 855 across the 81 of their papers we have counts for
3 papers · 1 filter
Revisiting Differentially Private Regression: Lessons From Learning Theory and their Consequences
Xi Wu, Matthew Fredrikson, Wentao Wu +2
Private regression has received attention from both database and security communities. Recent work by Fredrikson et al. (USENIX Security 2014) analyzed the functional mechanism (Zh…
The Limitations of Deep Learning in Adversarial Settings
Nicolas Papernot, Patrick McDaniel, Somesh Jha +3
Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfe…
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
Nicolas Papernot, Patrick McDaniel, Xi Wu +2
Deep learning algorithms have been shown to perform extremely well on many classical machine learning problems. However, recent studies have shown that deep learning, like other ma…