RABA: A Robust Avatar Backdoor Attack on Deep Neural Network.
Year: 2021
Type: preprint
Abstract: With the development of Deep Neural Network (DNN), as well as the demandgrowth of third-party DNN model stronger, there leaves a gap for backdoor
attack. Backdoor can be injected into a third-party model and has strong
stealthiness in normal situation, thus has been widely discussed. Nowadays
backdoor attack on deep neural network has been concerned a lot and there comes
lots of researches about attack and defense around backdoor in DNN. In this paper, we propose a robust avatar backdoor attack that integrated
with adversarial attack. Our attack can escape mainstream detection schemes
with popularity and impact that detect whether a model has backdoor or not
before deployed. It reveals that although many effective backdoor defense
schemes has been put forward, backdoor attack in DNN still needs to be
concerned. We select three popular datasets and two detection schemes with high
impact factor to prove that our attack has a great performance in aggressivity
and stealthiness.
Source: arXiv (Cornell University)
Authors: Ying He, Zhili Shen, Chang Xia, Jingyu Hua, Wei Tong, Sheng Zhong
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3162049398