Skip to main navigation
Skip to search
Skip to main content
Korea University Pure Home
Home
Profiles
Research units
Research output
Press/Media
Search by expertise, name or affiliation
γ-Knife: Extracting Neural Network Architecture Through Software-Based Power Side-Channel
Dohyun Ryu, Yerim Kim,
Junbeom Hur
Research output
:
Contribution to journal
›
Article
›
peer-review
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'γ-Knife: Extracting Neural Network Architecture Through Software-Based Power Side-Channel'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Neural Network
100%
Software-based
100%
Neural Network Architecture
100%
Knife
100%
Power Side-channel
100%
Side-channel Attacks
80%
Knife Attack
80%
Private Information
60%
Target Architecture
60%
Search Space
40%
Hardware Efficiency
40%
Side Channel
40%
Physical Access
40%
Power Consumption
20%
Measuring Equipment
20%
Activation Function
20%
Statistical Measures
20%
System Behavior
20%
Filter Length
20%
Physical Systems
20%
High-precision Measurement
20%
Power Data
20%
GoogLeNet
20%
Convolutional Layer
20%
U-Net
20%
Intel CPUs
20%
VGGNet
20%
High Resolving Power
20%
PyTorch
20%
MobileNet
20%
Cache Side Channel
20%
Model Information
20%
Electromagnetic Emanation
20%
Precision Equipment
20%
Convolutional Activations
20%
Computer Science
VGGNet
16%