Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

The purpose and operation of each event.

More »

Table 1 Expand

Fig 1.

Classification framework for APT malicious software based on multi-feature fusion.

More »

Fig 1 Expand

Fig 2.

Typical malicious software behavior of the APT30 family.

More »

Fig 2 Expand

Fig 3.

APT30 sample behavior of creating forged Word files.

More »

Fig 3 Expand

Fig 4.

Connecting to a remote C&C server.

More »

Fig 4 Expand

Fig 5.

Generating malicious executable files of APT30 samples.

More »

Fig 5 Expand

Fig 6.

Deleting the malicious executable file generated by the APT30 sample.

More »

Fig 6 Expand

Fig 7.

Typical malicious software behavior of the DarkHotel family.

More »

Fig 7 Expand

Fig 8.

Connecting to the remote malicious domain.

More »

Fig 8 Expand

Fig 9.

Traversing the system process list.

More »

Fig 9 Expand

Fig 10.

Generating a malicious executable file for encryption and authentication purposes.

More »

Fig 10 Expand

Fig 11.

Generate a disguised acroproedit file for the Dark Hotel sample.

More »

Fig 11 Expand

Fig 12.

Process behavior information in json reports.

More »

Fig 12 Expand

Fig 13.

APT malware code snippet.

More »

Fig 13 Expand

Fig 14.

The behavior graph of the code snippet.

More »

Fig 14 Expand

Fig 15.

Directed multi-edge behavior isomorphism graph.

More »

Fig 15 Expand

Table 2.

Operating system resource types and API calls.

More »

Table 2 Expand

Table 3.

Primary extracted opcodes.

More »

Table 3 Expand

Fig 16.

The opcode frequency co-occurrence matrix image.

More »

Fig 16 Expand

Fig 17.

Behavior graph feature engineering module.

More »

Fig 17 Expand

Fig 18.

Details of operations in the GGNN network.

More »

Fig 18 Expand

Fig 19.

ImageCNTM model.

More »

Fig 19 Expand

Table 4.

APT family and sample size.

More »

Table 4 Expand

Table 5.

Comparison of related papers based on dynamic behavior models.

More »

Table 5 Expand

Table 6.

Comparison of related papers based on static structural models.

More »

Table 6 Expand

Table 7.

Comparison of APT malware related papers.

More »

Table 7 Expand

Fig 20.

Confusion matrix for multiple classifications of APT malware.

More »

Fig 20 Expand

Fig 21.

Original features.

More »

Fig 21 Expand

Fig 22.

The t-SNE plot after passing through the classification layer.

More »

Fig 22 Expand

Fig 23.

Ablation study of graph learning model.

More »

Fig 23 Expand

Fig 24.

Ablation study of image learning model.

More »

Fig 24 Expand

Fig 25.

Comparison of multi-feature fusion modules.

More »

Fig 25 Expand

Fig 26.

Comparison of single-feature and multi-feature fusion modules.

More »

Fig 26 Expand