.png){kind=icon}
.png){kind=icon}
Return
Taking AI-Based Side-Channel Attacks to a New Dimension
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-01405-4_21.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper revisits the Hamming Weight (HW) labelling function for machine learning assisted side channel attacks. Contrary to what has been suggested by pervious works, our investigation shows that, when paired with modern deep learning architectures, appropriate per-processing and normalization techniques; it can perform as well as the popular identity labelling functions and sometimes even beat it. In fact, we hereby introduce a new machine learning method, dubbed dimension 0, that helps solve the class imbalance problem associated to HW, while significantly improving the performance of unprofiled attacks. We additionally release our new, easy to use python package that we used in our experiments, implementing a broad variety of machine learning driven side channel attacks as open source, along with a new dataset AES_nRF, acquired on the nRF52840 SoC.
Keywords:
Profiled and Unprofiled Side-Channel Attacks
Deep Learning
Softmax Function
Journal
C
IF:
0
Papers:
23
Citations:
0