Work

Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification

Year: 2017
Type: conference-paper
Abstract: Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to adversarial manipulations at testing time. Specifically, suppose we have a testing example, whose label can be correctly predicted by a DNN classifier. An attacker can add a small carefully crafted noise to the testing example such that the DNN classifier predicts an incorrect label, where the crafted testing example is called adversarial example. Such attacks are called evasion attacks. Evasion attacks are one of the biggest challenges for deploying DNNs in safety and security critical applications such as self-driving cars.
Language: English
Open Access status: green
OpenAlex ID: W2754049786
FWCI: 7.929
Cites: 38
Cited by: 234
Related to: 9