Detection and defense method based on FGSM anti-attack algorithm
An algorithm and anti-sample technology, applied in the computer field, can solve problems such as the safety of life and property
Active Publication Date: 2020-08-28
NINGBO TRANSMISSION & DISTRIBUTION CONSTR +4
View PDF6 Cites 21 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
If the left-turn sign is attacked and recognized as a right-turn sign, or the stop sign is attacked and recognized as continuing to drive, it will cause huge life and property safety
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0058] The invention provides a detection and defense method based on the FGSM counterattack algorithm, such as figure 1 shown, including:
[0059] Step 1: Determine the original image sample being attacked;
[0060] Step 2: Input the original image sample into the network model, and use the FGSM algorithm to generate an adversarial image sample;
[0061] Step 3: Input the original image sample into the target network model, and train the target recognition network;
[0062] Step 4: Input the original image samples and adversarial image samples into the detection model, use the DCT algorithm and the SVM algorithm to train the model and perform detection;
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
Login to View More Abstract
The invention provides a detection and defense method based on an FGSM anti-attack algorithm. The detection and defense method comprises the following steps: determining an attacked original image sample; inputting the original image sample into a network model, and generating an adversarial image sample by using an FGSM algorithm; inputting the original image sample into a target network model, and training a target recognition network; inputting the original image sample and the adversarial image sample into a detection model, training the model by using a DCT algorithm and an SVM algorithm,and performing detection; and testing the image sample to be tested, and outputting an identification result. An FGSM algorithm is used to generate an adversarial image sample, a training pre-input layer mode is called to detect a test sample, a target network model is used to carry out identification, and defense capability aiming at introduced disturbance is increased.
Description
technical field [0001] The invention belongs to the field of computers, in particular to a detection and defense method based on an FGSM anti-attack algorithm. Background technique [0002] With the rapid development of technology in the field of machine vision, more and more applications have also landed. The ultimate goal of machine vision is to create machine eyes that can recognize things in this world like human eyes. The core of which is the deep neural network system. Machine vision is one of the most rapidly developing directions of deep learning. [0003] But with the development of machine learning computer vision, the security of machine learning algorithms has also received extensive attention. In image recognition, some carefully crafted perturbations can be added to the original image to make it imperceptible to the human eye, but can trick the neural network into misclassifying it. The characteristic of adversarial examples is to find as small a disturbanc...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): H04L29/06
CPCH04L63/1416H04L63/1441
Inventor 徐嘉龙董建达夏洪涛李鹏高明王猛徐重酉叶楠苏建华赵剑叶斌琚小明张朋飞于晓蝶冉清文刘宇潘富城胡妙
Owner NINGBO TRANSMISSION & DISTRIBUTION CONSTR