Software supply chain malicious software detection method based on LSTM-BO-SVM and application

The invention discloses software supply chain malicious software detection based on LSTM-BO-SVM, and relates to the field of malicious software detection. Comprising the steps of 1, obtaining software supply chain software to be detected; 2, an LSTM-BO-SVM model is constructed, and the LSTM-BO-SVM m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHOU SHUNCHENG, FU XUELIANG, LI HONGHUI, MA LILI
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses software supply chain malicious software detection based on LSTM-BO-SVM, and relates to the field of malicious software detection. Comprising the steps of 1, obtaining software supply chain software to be detected; 2, an LSTM-BO-SVM model is constructed, and the LSTM-BO-SVM model is trained and evaluated; step 3, inputting the software supply chain software to be detected into the trained LSTM-BO-SVM model; and step 4, outputting a final detection result. According to the method, SSC malicious software classification is carried out by utilizing the BO-SVM model, automatic search of the optimal hyper-parameters of the SVM model is realized, and the detection efficiency and accuracy of the SSC malicious software are improved; and a new classification model LSTM-BO-SVM is provided, the features of the malicious software can be captured more comprehensively through the model, and the detection precision of the malicious software in the SSC is further improved. 本发明公开了一种基于LSTM-BO-SVM的软件供应链恶意