Mathematics

Gene

Data mining

Machine learning

Mathematical analysis

Political science

Artificial intelligence

Differential privacy

Chemistry

Computer science

Certification

Malware

Theoretical computer science

Bounded function

Adversarial system

Computer security

Artificial neural network

Biochemistry

Robustness (evolution)

Adversarial examples that fool machine learning models, particularly deep neural networks, have been a topic of intense research interest, with attacks and defenses being developed in a tight back-and-forth. Most past defenses are best effort and have been shown to be vulnerable to sophisticated attacks. Recently a set of certified defenses have been introduced, which provide guarantees of robustness to norm-bounded attacks. However these defenses either do not scale to large datasets or are limited in the types of models they can support. This paper presents the first certified defense that both scales to large networks and datasets (such as Google's Inception network for ImageNet) and applies broadly to arbitrary model types. Our defense, called PixelDP, is based on a novel connection between robustness against adversarial examples and differential privacy, a cryptographically-inspired privacy formalism, that provides a rigorous, generic, and flexible foundation for defense.

Certified Robustness to Adversarial Examples with Differential Privacy