Evaluation and Design of Robust Neural Network Defenses

By Nicholas Carlini. 2018

6 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. Florian Tramèr
2. Dan Boneh
3. Edward Chou
4. Giancarlo Pellegrino
5. Brent Waters
6. Allison Bishop
7. Xavier Boyen
8. Craig Gentry

Citations in the corpus

• SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems (2018, background): “ges in the LISA dataset—stop signs are often cropped to sizes as small as 30 30. Nevertheless, SentiNet still produces detection accuracies comparable to other adversarial detection works (see, e.g., [5]). Attack #2: Trojaned Networks—A trojaning attack generates a trigger from specified neurons in t”
• SentiNet: Detecting Physical Attacks Against Deep Learning Systems (2018, background): “Nevertheless, SentiNet still produces detection accuracies comparable to other adversarial detection works (see, e.g., [5]).”