CN109543406B - Android malicious software detection method based on XGboost machine learning algorithm - Google Patents
Android malicious software detection method based on XGboost machine learning algorithm Download PDFInfo
- Publication number
- CN109543406B CN109543406B CN201811150736.1A CN201811150736A CN109543406B CN 109543406 B CN109543406 B CN 109543406B CN 201811150736 A CN201811150736 A CN 201811150736A CN 109543406 B CN109543406 B CN 109543406B
- Authority
- CN
- China
- Prior art keywords
- xgboost
- algorithm
- malicious software
- child
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/55—Detecting local intrusion or implementing counter-measures
- G06F21/56—Computer malware detection or handling, e.g. anti-virus arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention relates to an Android malicious software detection method based on an XGboost machine learning algorithm. Compared with the traditional XGboost algorithm, the improved XGboost machine learning algorithm provided by the invention has higher classification precision in the detection of the Android malicious software, improves the accuracy of the detection of the malicious software, and reduces the probability of attack on the Android system caused by detection errors.
Description
Technical Field
The invention relates to the technical field of malicious software detection on an Android platform, in particular to an Android malicious software detection method based on an XGboost machine learning algorithm.
Background
The Android system is formally released by Google corporation in 2007, 11 month and 5 days, and as an operating system based on a Linux kernel, the Android system has the characteristics of being open-source and free, so that the Android system becomes an operating system of an intelligent mobile device with the largest market occupation amount at an extremely high speed. However, while it is popular with a wide range of App developers and users, it is also a preferred target for malicious attackers. The rapid growth of Android malicious software seriously threatens the safety and privacy of users, the malicious software steals private data of the users, property loss is caused, higher authority is obtained by using system bugs, and greater harm is realized. With the continuous advance of the mobile payment industry, the concept of internet and mobile payment explodes, mobile payment develops rapidly, and viruses paid by mobile phones emerge endlessly, which seriously endangers the property safety of users. There is therefore a need for a method of quickly and efficiently detecting malware.
At present, three detection methods for Android malicious software are mainly used, namely a static detection method, a dynamic detection method and a method combining static detection and dynamic detection.
The static detection method includes the steps that under the condition that the Android application program is not operated, the installation package of the application program is decompiled through reverse engineering, and relevant features such as authority information, API calling and instruction features are extracted, so that possible operation of the program during operation can be represented, and whether the application program is malicious software or not is judged. Static detection mostly uses a machine learning algorithm to perform classification detection on the extracted feature information. However, the classification accuracy of the static detection method is not high, the accuracy of malicious software detection is low, and the probability that the Android system is attacked due to detection errors is increased.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an Android malicious software detection method based on an XGboost machine learning algorithm, which has the advantages of higher classification precision and higher malicious software detection accuracy and greatly reduces the probability of the Android system being attacked due to detection errors.
In order to achieve the purpose, the technical scheme provided by the invention is as follows:
a method for detecting Android malicious software based on an XGboost machine learning algorithm comprises the steps of extracting the characteristics of Permission, intent, component and API call through decompiling an apk file, quantizing the characteristics to form a characteristic matrix, performing parameter optimization on an XGboost integrated learning framework by using an ant colony optimization algorithm, quickly finding out a global optimal solution, obtaining an optimal target value after multiple iterations, obtaining an optimal parameter combination contraction step length shrinkage of the XGboost and a minimum sample weight threshold value min _ child _ weight in a child node, and finally applying the optimized XGboost algorithm to an Android malicious software detection model.
Further, the Android malicious software detection method based on the XGboost machine learning algorithm comprises the following specific steps:
s1: decompiling the apk file by using the apktool to obtain android manifest.xml and classes.dex;
s2: extracting the Permission, intent, component and API call characteristics;
s3: quantizing the features, wherein the output value is a one-hot vector, if the features exist, the vector is marked as 1, otherwise, the vector is marked as 0;
s4: forming a feature vector set by all feature vectors, reducing the dimension of the feature vector set by adopting a feature selection algorithm, and selecting an optimal feature subset;
s5: performing parameter optimization on the XGboost integrated learning framework by using an ant colony optimization algorithm, quickly finding out a global optimal solution, obtaining an optimal target value after multiple iterations, and obtaining an optimal parameter combination shrinkage step length shrinkage of the XGboost and a minimum sample weight threshold value min _ child _ weight in a child node;
s6: randomly extracting 10% of the optimized feature vectors as a test set, and inputting the rest 90% of the optimized feature vectors as a training set into an optimized XGboost integrated learning frame for optimized learning;
s7: and evaluating the classification result from the true rate, the false positive rate and the classification precision, and judging whether the XGboost algorithm optimized based on the ant colony algorithm is used for generating an Android malicious software detection model to meet the detection requirement.
Further, the specific steps of utilizing the ant colony optimization algorithm to optimize the parameters of the XGboost ensemble learning frame are as follows:
A. setting the contraction step length shrinkage of the XGboost classifier parameter and the upper and lower limits of the minimum sample weight threshold min _ child _ weight in the child node, the maximum iteration times MaxIter, the ant colony scale M and the information evaporation coefficient Rho;
B. initializing populations, namely initializing shrinkage and min _ child _ weight as a position vector of each ant;
C. executing ant colony search;
D. XGboost training is carried out;
E. calculating the objective function value and the pheromone value of each ant by using an XGboost classifier, and searching the current optimal ant;
F. judging whether a termination condition is met: if the iteration times are larger than the MaxIter, outputting an ant colony optimal value and corresponding shrinkage and min _ child _ weight values, executing the step G, and if not, adding 1 to the iteration times, and executing the step C;
G. updating the pheromone;
H. and using the output shrinkage and min _ child _ weight in a detection model of the Android malware.
Further, the ant colony optimization algorithm is specifically as follows:
ant colony position initialization:
the classification accuracy of XGboost is assumed as the objective function value
max{F(s 1 ,w 1 ),F(s 2 ,w 2 ),...,F(s m ,w m ) Is denoted as max (ness = max { F (X) }, X = { X = { (X) } 1 ,x 2 ,...,x m In which x i Expressing ants, and generating an initialized population by using the chaotic sequence comprises the following steps:
1) Generating a random vector in D dimension:
2) Logitics mapping, using the above formula as an initial iteration, the Logitics mapping equation is as follows:
wherein μ =1, i =1, 2., N, D =1,2, ·, D;
3) Mapping the chaotic space to a search space of an optimized variable:
in the formula, max d To take the upper limit, min d Taking a lower limit value;
the ant moving rule is as follows:
after the ant colony is initialized, the objective function is calculated,defining the position vector of the jth ant in the kth iteration, wherein the larger the objective function is, the larger the concentration of the position pheromone is, and storing the ant with the maximum current target value as ^ based on the judgment result>And its pheromone maximum->
Selecting local search or global search:
the probability of ant transfer is defined as follows:
in the formula, S is a standard deviation of the fitness function, and the calculation formula is as follows:
wherein m is the number of ants, F ave Is the average fitness value;
from the above formula, it is known thatThe closer the ants are, the greater the transfer probability is, and the searching method is as follows:
if P (x) i ) P0 or less, wherein P0 is constant, 0<P0<1, the ant searches nearby local positions, and the movement formula is as follows:
in the formulaFor the moved position, is>For the position before the movement, a is the movement step, defined as follows:
if P (x) i ) If the answer is more than P0, the ants search in the solution space;
and (3) updating pheromone:
according to the size of the individual position function value, the update pheromone is as follows:
where ρ is an information evaporation coefficient.
Compared with the prior art, the principle and the advantages of the scheme are as follows:
compared with the traditional XGboost machine learning algorithm, the performance of XGboost algorithm classification is influenced by parameter selection in Android malicious software detection, the method and the device have the advantages that the ant colony algorithm is applied to optimize the parameters of the XGboost, the optimal parameters are quickly found, the XGboost algorithm has good classification performance, and the XGboost algorithm is applied to an Android malicious software detection model, so that the higher classification precision is realized during the Android malicious software detection, the malicious software detection accuracy is greatly improved, and the probability that an Android system is attacked due to detection errors is reduced.
Drawings
FIG. 1 is a detection flow chart of an Android malicious software detection method based on an XGboost machine learning algorithm according to the invention;
FIG. 2 is a flow chart of feature extraction in an Android malicious software detection method based on an XGboost machine learning algorithm of the invention;
fig. 3 is a flowchart of optimizing XGBoost parameters by using an ant colony algorithm in the Android malware detection method based on the XGBoost machine learning algorithm of the present invention.
Detailed Description
The invention will be further illustrated with reference to specific examples:
the Android malicious software detection method based on the XGboost machine learning algorithm described in this embodiment specifically includes the following contents:
an integrated learning algorithm proposed by Tian Chen in 2015 in XGboost (eXtreme Gradient Boosting) has the main parameters of shrinking step length (shrinkage) and minimum sample weight threshold (min _ child _ weight) in child nodes, which directly influence the classification performance, in an XGboost integrated learning framework. Too small a shrinkage will cause the algorithm to overfit, larger shrinkage will cause the algorithm to fail to converge, too small a shrinkage will cause the algorithm to overfit for min _ child _ weight, and too large mini _ child _ weight will cause the algorithm to classify linear irreparable data.
Therefore, in the embodiment, after feature matrixes are formed by inversely compiling apk files and extracting the Permission, intent, component and API call feature quantization, an ant colony optimization algorithm is used for performing parameter optimization on the XGBoost ensemble learning frame, a global optimal solution is quickly found, an optimal target value is obtained after multiple iterations, an optimal parameter combination contraction step shrinkage of the XGBoost and a minimum sample weight threshold min _ child _ weight in a child node are obtained, and finally the optimized XGBoost algorithm is applied to the Android malicious software detection model. As shown in fig. 1, the specific steps are as follows:
s1: decompiling the apk file by using the apktool to obtain android manifest.xml and classes.dex;
s2: extracting the Permission, intent, component and API call characteristics, wherein the specific process is shown in FIG. 2;
s3: quantizing the features, wherein the output value is a one-hot vector, if the features exist, the vector is marked as 1, otherwise, the vector is marked as 0;
s4: forming a feature vector set by all feature vectors, reducing the dimension of the feature vector set by adopting a feature selection algorithm, and selecting an optimal feature subset;
s5: performing parameter optimization on the XGboost integrated learning framework by using an ant colony optimization algorithm, quickly finding out a global optimal solution, obtaining an optimal target value after multiple iterations, and obtaining an optimal parameter combination shrinkage step length shrinkage of the XGboost and a minimum sample weight threshold value min _ child _ weight in a child node;
s6: randomly extracting 10% of the optimized feature vectors as a test set, and inputting the rest 90% of the optimized feature vectors as a training set into an optimized XGboost integrated learning frame for optimized learning;
s7: and evaluating the classification result from the true rate, the false positive rate and the classification precision, and judging whether the XGboost algorithm optimized based on the ant colony algorithm is used for generating an Android malicious software detection model to meet the detection requirement.
In the above, as shown in fig. 3, the specific steps of performing parameter optimization on the XGBoost ensemble learning framework by using the ant colony optimization algorithm are as follows:
A. setting the contraction step length shrinkage of the XGboost classifier parameter and the upper and lower limits of the minimum sample weight threshold min _ child _ weight in the child node, the maximum iteration times MaxIter, the ant colony scale M and the information evaporation coefficient Rho;
B. initializing populations, namely initializing shrinkage and min _ child _ weight as a position vector of each ant;
C. executing ant colony search;
D. XGboost training is carried out;
E. calculating the objective function value and the pheromone value of each ant by using an XGboost classifier, and searching the current optimal ant;
F. judging whether a termination condition is met: if the iteration times are larger than the MaxIter, outputting an ant colony optimal value and corresponding shrinkage and min _ child _ weight values, executing the step G, and if not, adding 1 to the iteration times, and executing the step C;
G. updating the pheromone;
H. and using the output shrinkage and min _ child _ weight in a detection model of the Android malware.
The specific ant colony optimization algorithm is as follows:
ant colony position initialization:
the classification accuracy of XGboost is assumed as the objective function value
max{F(s 1 ,w 1 ),F(s 2 ,w 2 ),...,F(s m ,w m ) Is denoted as max (ness = max { F (X) }, X = { X = { (X) } 1 ,x 2 ,...,x m In which x i Expressing ants, and generating an initialized population by using the chaotic sequence as follows:
1) Generating a random vector in D dimension:
2) Logitics mapping, using the above formula as an initial iteration, the Logitics mapping equation is as follows:
wherein μ =1, i =1, 2., N, D =1,2, ·, D;
3) Mapping the chaotic space to a search space of an optimized variable:
in the formula, max d To take the upper limit, min d Taking a lower limit value;
the ant moving rule is as follows:
after the ant colony is initialized, the objective function is calculated,defining the position vector of the jth ant in the kth iteration, wherein the larger the objective function is, the larger the concentration of the position pheromone is, and storing the ant with the maximum current target value as ^ based on the judgment result>And its pheromone maximum->
Selecting local search or global search:
the probability of ant transfer is defined as follows:
in the formula, S is a standard deviation of the fitness function, and the calculation formula is as follows:
wherein m is the number of ants, F ave Is the average fitness value;
from the above formula, it is known thatThe closer the ants are, the greater the transfer probability is, and the searching method is as follows:
if P (x) i ) P0 or less, wherein P0 is constant, 0<P0<1, the ant searches nearby local positions, and the movement formula is as follows:
in the formulaFor the moved position, is>For the position before the movement, a is the movement step, defined as follows:
if P (x) i ) If the answer is more than P0, the ants search in the solution space;
and (3) updating pheromone:
according to the size of the individual position function value, the update pheromone is as follows:
where ρ is an information evaporation coefficient.
According to the method, firstly, permission, intent, component and API call characteristics are extracted through decompiling an apk file, a characteristic matrix is formed in a quantization mode, and parameters of the XGboost classifier are optimized by utilizing the parallelism and the strong robustness of an ant colony algorithm, so that an optimal target is obtained, and an optimal parameter combination of the XGboost is obtained. Compared with the traditional XGboost algorithm, the improved XGboost machine learning algorithm provided by the embodiment has higher classification precision in the detection of the Android malicious software, improves the accuracy of the detection of the malicious software, and reduces the probability of the attack on the Android system caused by the detection error.
The above-mentioned embodiments are merely preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, so that variations based on the shape and principle of the present invention should be covered within the scope of the present invention.
Claims (2)
1. An Android malicious software detection method based on an XGboost machine learning algorithm is characterized in that Permission, intent, component and APIcall characteristics are extracted by decompiling an apk file, a characteristic matrix is formed in a quantized mode, an ant colony optimization algorithm is used for carrying out parameter optimization on an XGboost integrated learning framework, a global optimal solution is quickly found, an optimal target value is obtained after multiple iterations, an optimal parameter combination contraction step length shrinkage of the XGboost and a minimum sample weight threshold value min _ child _ weight in a child node are obtained, and finally the optimized XGboost algorithm is applied to an Android malicious software detection model;
the method specifically comprises the following steps:
s1: decompiling the apk file by using the apktool to obtain android manifest.xml and classes.dex;
s2: extracting the Permission, intent, component and API call characteristics;
s3: quantizing the features, wherein the output value is a one-hot vector, if the features exist, the vector is marked as 1, otherwise, the vector is marked as 0;
s4: forming a feature vector set by all feature vectors, reducing the dimension of the feature vector set by adopting a feature selection algorithm, and selecting an optimal feature subset;
s5: performing parameter optimization on the XGboost integrated learning framework by using an ant colony optimization algorithm, quickly finding out a global optimal solution, obtaining an optimal target value after multiple iterations, and obtaining an optimal parameter combination shrinkage step length shrinkage of the XGboost and a minimum sample weight threshold value min _ child _ weight in a child node;
s6: randomly extracting 10% of the optimized feature vectors as a test set, and inputting the rest 90% of the optimized feature vectors as a training set into an optimized XGboost integrated learning frame for optimized learning;
s7: and evaluating the classification result from the true rate, the false positive rate and the classification precision, and judging whether the Android malicious software detection model generated by the XGboost algorithm optimized based on the ant colony algorithm meets the detection requirement.
2. The Android malicious software detection method based on the XGboost machine learning algorithm as claimed in claim 1, wherein the specific steps of using the ant colony optimization algorithm to perform parameter optimization on the XGboost ensemble learning frame are as follows:
A. setting the contraction step length shrinkage of the XGboost classifier parameter and the upper and lower limits of the minimum sample weight threshold min _ child _ weight in the child node, the maximum iteration times MaxIter, the ant colony scale M and the information evaporation coefficient Rho;
B. initializing populations, namely initializing shrinkage and min _ child _ weight as a position vector of each ant;
C. executing ant colony search;
D. XGboost training is carried out;
E. calculating the objective function value and the pheromone value of each ant by using an XGboost classifier, and searching the current optimal ant;
F. judging whether a termination condition is met: if the iteration times are larger than the MaxIter, outputting an ant colony optimal value and corresponding shrinkage and min _ child _ weight values, executing the step G, and if not, adding 1 to the iteration times, and executing the step C;
G. updating the pheromone;
H. and using the output shrinkage and min _ child _ weight in a detection model of the Android malicious software.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811150736.1A CN109543406B (en) | 2018-09-29 | 2018-09-29 | Android malicious software detection method based on XGboost machine learning algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811150736.1A CN109543406B (en) | 2018-09-29 | 2018-09-29 | Android malicious software detection method based on XGboost machine learning algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109543406A CN109543406A (en) | 2019-03-29 |
CN109543406B true CN109543406B (en) | 2023-04-11 |
Family
ID=65841391
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811150736.1A Active CN109543406B (en) | 2018-09-29 | 2018-09-29 | Android malicious software detection method based on XGboost machine learning algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109543406B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110197068B (en) * | 2019-05-06 | 2022-07-12 | 广西大学 | Android malicious application detection method based on improved grayish wolf algorithm |
CN110263539A (en) * | 2019-05-15 | 2019-09-20 | 湖南警察学院 | A kind of Android malicious application detection method and system based on concurrent integration study |
CN110362995B (en) * | 2019-05-31 | 2022-12-02 | 电子科技大学成都学院 | Malicious software detection and analysis system based on reverse direction and machine learning |
CN112818344A (en) * | 2020-08-17 | 2021-05-18 | 北京辰信领创信息技术有限公司 | Method for improving virus killing rate by applying artificial intelligence algorithm |
CN112989342B (en) * | 2021-03-04 | 2022-08-05 | 北京邮电大学 | Malicious software detection network optimization method and device, electronic equipment and storage medium |
CN115801463B (en) * | 2023-02-06 | 2023-04-18 | 山东能源数智云科技有限公司 | Industrial Internet platform intrusion detection method and device and electronic equipment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194803A (en) * | 2017-05-19 | 2017-09-22 | 南京工业大学 | A kind of P2P nets borrow the device of borrower's assessing credit risks |
CN107577942A (en) * | 2017-08-22 | 2018-01-12 | 中国民航大学 | A kind of composite character screening technique for Android malware detection |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6701311B2 (en) * | 2001-02-07 | 2004-03-02 | International Business Machines Corporation | Customer self service system for resource search and selection |
US8108933B2 (en) * | 2008-10-21 | 2012-01-31 | Lookout, Inc. | System and method for attack and malware prevention |
-
2018
- 2018-09-29 CN CN201811150736.1A patent/CN109543406B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194803A (en) * | 2017-05-19 | 2017-09-22 | 南京工业大学 | A kind of P2P nets borrow the device of borrower's assessing credit risks |
CN107577942A (en) * | 2017-08-22 | 2018-01-12 | 中国民航大学 | A kind of composite character screening technique for Android malware detection |
Non-Patent Citations (1)
Title |
---|
基于机器学习的移动终端高级持续性威胁检测技术研究;胡彬等;《计算机工程》;20170115(第01期);242-246 * |
Also Published As
Publication number | Publication date |
---|---|
CN109543406A (en) | 2019-03-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109543406B (en) | Android malicious software detection method based on XGboost machine learning algorithm | |
US10867038B2 (en) | System and method of detecting malicious files with the use of elements of static analysis | |
CN106899440B (en) | Network intrusion detection method and system for cloud computing | |
CN105989288A (en) | Deep learning-based malicious code sample classification method and system | |
US11256804B2 (en) | Malware classification of executable files by convolutional networks | |
KR102317833B1 (en) | method for machine LEARNING of MALWARE DETECTING MODEL AND METHOD FOR detecting Malware USING THE SAME | |
CN111914253B (en) | Method, system, equipment and readable storage medium for intrusion detection | |
CN111368289B (en) | Malicious software detection method and device | |
CN112673386A (en) | Integration-based data management pipeline for efficient tag propagation | |
CN112395612A (en) | Malicious file detection method and device, electronic equipment and storage medium | |
KR102058966B1 (en) | Method for detecting malicious application and apparatus thereof | |
CN114692156A (en) | Memory segment malicious code intrusion detection method, system, storage medium and equipment | |
US20170091451A1 (en) | Creating rules describing malicious files based on file properties | |
CN116522338A (en) | File processing method, equipment and computer readable storage medium | |
CN111382432A (en) | Malicious software detection and classification model generation method and device | |
CN115081618A (en) | Method and device for improving robustness of deep neural network model | |
CN108229168B (en) | Heuristic detection method, system and storage medium for nested files | |
CN113868647A (en) | Network unknown threat detection method based on feature extension CNN | |
CN110197068B (en) | Android malicious application detection method based on improved grayish wolf algorithm | |
KR20200067044A (en) | Method and apparatus for detecting malicious file | |
Yuan et al. | Android applications categorization using bayesian classification | |
CN114238944A (en) | File type determination method, device, equipment and medium | |
CN107622201A (en) | A kind of Android platform clone's application program quick determination method of anti-reinforcing | |
De Lille et al. | Automatically combining static malware detection techniques | |
Prabhavathi et al. | Malware Prediction Using XGBOOST and CATBOOST |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |