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

Fig 1.

Working process of fuzzing.

More »

Fig 1 Expand

Table 1.

Data extraction form items.

More »

Table 1 Expand

Fig 2.

Flowchart of the systematic review process.

More »

Fig 2 Expand

Table 2.

Selected primary studies in the field of machine learning based fuzzing.

More »

Table 2 Expand

Table 3.

Distribution of research literature based on machine learning for different steps of fuzzing.

More »

Table 3 Expand

Table 4.

Distribution of machine learning arithmetics for fuzzing.

More »

Table 4 Expand

Table 5.

Pre-processing methods for machine learning techniques in fuzzing.

More »

Table 5 Expand

Table 6.

Evaluation metrics and details for machine learning models in fuzzing.

More »

Table 6 Expand

Table 7.

Evaluation metrics and details for fuzzers based on machine learning.

More »

Table 7 Expand

Table 8.

Analysis of hyperparameters setting of machine learning models for fuzzing.

More »

Table 8 Expand

Fig 3.

Comparison of Accuracy between different models.

More »

Fig 3 Expand

Fig 4.

Comparison of Precision between different models.

More »

Fig 4 Expand

Fig 5.

Comparison of Recall between different models.

More »

Fig 5 Expand

Fig 6.

Comparison of Loss between different models.

More »

Fig 6 Expand

Table 9.

Results of cove coverage improvement of fuzzers based on machine learning.

More »

Table 9 Expand

Table 10.

Results of Machine learning-based fuzzers compared to baselines in unique crashes and bugs discovery.

More »

Table 10 Expand

Table 11.

Statistics on the number of vulnerabilities found on LAVA-M dataset by machine learning-based fuzzers and traditional fuzzers.

More »

Table 11 Expand

Table 12.

Results of efficiency improvement of fuzzers based on machine learning.

More »

Table 12 Expand