![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Chapter and Conference Paper
Efficient Black-Box Adversarial Attacks with Training Surrogate Models Towards Speaker Recognition Systems
Speaker Recognition Systems (SRSs) are gradually introducing Deep Neural Networks (DNNs) as their core architecture, while attackers exploit the weakness of DNNs to launch adversarial attacks. Previous studies...
-
Chapter and Conference Paper
An Android Malware Detection Method Based on Metapath Aggregated Graph Neural Network
Android system is facing an increasing threat of malware. Most of the current malware detection systems need to use large-scale training samples to get high accuracy. However, it is difficult to get a lot of s...
-
Chapter and Conference Paper
A Label Flip** Attack on Machine Learning Model and Its Defense Mechanism
Recently, the robustness of machine learning against data poisoning attacks is widely concerned. As a subclass of poisoning attack, the label flip** attack can poison training data resulting in reducing the ...
-
Chapter and Conference Paper
Worm Propagation Modeling and Analysis on Network
In recent years, network worms that had a dramatic increase in the frequency and virulence of such outbreaks have become one of the major threats to the security of the Internet. This paper provides a worm pro...