On the Connection between Differential Privacy and Adversarial Robustness in Machine Learning

By Mathias Lécuyer, Vaggelis Atlidakis, Roxana Geambasu, Daniel J. Hsu, Suman Sekhar Jana. 2018

20 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Lawrence Carin
2. Changyou Chen
3. Wenlin Wang
4. Chunyuan Li
5. Adnan Siraj Rakin
6. Zhezhi He
7. Deliang Fan
8. Bai Li

Citations in the corpus

• Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack (2018, background): “In order to make the model more robust to adversarial attack, several works have adopted the concept of adding a noise layer just before convolution layer during both training and inference phases [29, 38].”
• Certified Adversarial Robustness with Additive Noise (2018, methodology): “umptions, such as on the structure of the model or on the smoothness of the loss function, or are difficult to extend to large-scale data sets, the most common application scenario for DNNs. Recently, Mathias et al. (2018) developed theoretical insight of certifiable robust prediction, by building a c”
• Second-Order Adversarial Attack and Certifiable Robustness (2018, methodology): “The simulation result shows our bound is strictly higher than the one from PixelDP.”