Search Results for author:
Found 3 papers, 0 papers with code
Spectrum Data Poisoning with Adversarial Deep Learning
We consider the case that a cognitive transmitter senses the spectrum and transmits on idle channels determined by a machine learning algorithm.
Generative Adversarial Networks for Black-Box API Attacks with Limited Training Data
The exploratory attack with limited training data is shown to fail to reliably infer the target classifier of a real text classifier API that is available online to the public.
BIG-bench Machine Learning
Generative Adversarial Network
+1
Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls
To mitigate the impact of limited training data, we develop an active learning approach that first builds a classifier based on a small number of API calls and uses this classifier to select samples to further collect their labels.
