Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A learned side-channel attack method and encryption device for automatically discovering leaked models

A side-channel attack and automatic discovery technology, applied in the field of side-channel attack methods and encryption equipment, can solve problems such as side-channel high-level attacks, improve reliability, avoid manual reasoning or guessing, and improve analysis efficiency

Active Publication Date: 2022-07-22
CHENGDU UNIV OF INFORMATION TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Solve side-channel high-level attacks that are currently almost impossible to implement

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A learned side-channel attack method and encryption device for automatically discovering leaked models
  • A learned side-channel attack method and encryption device for automatically discovering leaked models
  • A learned side-channel attack method and encryption device for automatically discovering leaked models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0079] In a specific embodiment, the intermediate combination value fitting network GVNet of the attack model is defined as the input layer width of 48, which is used to input a plaintext byte of [-1,1] encoded 8-bit data, a subkey byte of [-1,1] Encoded 8-bit data, encrypted intermediate value ROUND-IN, ADD-KEY, SBOX-IN and SBOX-OUT with one byte of [-1,1] encoding a total of 32-bit data; The layer is 3 fully connected layers with a width of 128, and the neuron activation function is tanh; the output layer is a fully connected layer with a width of 8 neurons, and the neuron activation function is tanh. The energy consumption combination value fitting network GENet is a convolutional upgrading network. The input layer size is 10000, which is used to input all energy consumption samples generated by the SBOX0 encryption process; 5 convolution blocks are used, and each convolution block contains a 1D convolutional layer with stride 2 and a 1D stride 2 max pooling layers. The a...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of cryptographic algorithm analysis and detection, and discloses a learning side channel attack method and an encryption device for automatically discovering a leaked model. The neural network of the attacking model is trained to find a combination form of an intermediate combination value of leaked key information. , and the corresponding energy consumption combination. The goal of training is to maximize the correlation between the intermediate combination value and the energy consumption combination value; in the attack phase, the attack model is used to identify the correctness of the guessed sub-key; according to the sub-key obtained by the attack, the master secret of the encryption device is recovered. key. In the attack stage, the invention uses the attack data set of the unknown key, and calculates the vector distance between the corresponding guess intermediate combination value and the energy consumption combination value by inputting the guess subkey into the attack model. The guessed sub-key with the smallest distance is selected as the correct sub-key. After obtaining the sub-keys one by one using the divide-and-conquer principle, the master key is inversely calculated to realize the attack on the master key of the encryption device.

Description

technical field [0001] The invention belongs to the technical field of cryptographic algorithm analysis and detection, and in particular relates to a learning side channel attack method and an encryption device for automatically discovering a leaked model. Background technique [0002] At present, encryption algorithms are the key means to ensure data security. Modern encryption algorithms are theoretically uncrackable or their cracking costs are too high, making cracking the key impractical. However, side-channel attacks pose a very serious challenge to the security of various encryption algorithms, so that the authentication of various encryption devices must pass the verification of side-channel attacks. The idea of ​​a side channel attack is that the energy consumption of a certain intermediate value calculation operation and access operation in the encryption calculation process is related to the value of the intermediate value, so the intermediate value can be identif...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F21/55G06F21/60G06N3/04G06N3/08
CPCG06F21/556G06F21/554G06F21/602G06N3/084G06N3/044G06N3/045
Inventor 杜之波
Owner CHENGDU UNIV OF INFORMATION TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products