What question did this study set out to answer?

The review aims to summarize the landscape of adversarial attacks and defenses in deep neural networks.

January 1, 2018Open Access

Adversarial Attacks and Defenses Against Deep Neural Networks: A Survey

Key Points

The review aims to summarize the landscape of adversarial attacks and defenses in deep neural networks.
Analyzed various types of adversarial attacks and defenses.
Reviewed state-of-the-art methods for targeting and safeguarding against adversarial input samples.
Examined top competition submissions from Neural Information Processing Systems in 2017.
Identified numerous vulnerabilities in deep neural networks exposed by adversarial examples.
Highlighted effective defense strategies against adversarial attacks, demonstrating varied performance.
Showcased notable models from the 2017 adversary competition that achieved significant results.

Abstract

Deep learning has achieved great successes in various types of applications over recent years. On the other hand, it has been found that deep neural networks (DNNs) can be easily fooled by adversarial input samples. This vulnerability raises major concerns in security-sensitive environments. Therefore, research in attacking and defending DNNs with adversarial examples has drawn great attention. The goal of this paper is to review the types of adversarial attacks and defenses, describe the state-of-the-art methods for each group, and compare their results. In addition, we present some of the top-scored competition submissions for Neural Information Processing Systems (NIPS) in 2017, their solution models, and demonstrate their results. This adversary competition was organized by Google Brain for research scientists to come up with novel solutions that generate adversarial examples and also defend against them. Its contribution is significant on this era of machine learning and DNNs.

Adversarial Attacks and Defenses Against Deep Neural Networks: A Survey

Key Points

Abstract

Cite This Study