Commit
•
383dc40
1
Parent(s):
b0db193
Update README.md
Browse files
README.md
CHANGED
@@ -33,13 +33,13 @@ tags:
|
|
33 |
## Overview
|
34 |
|
35 |
This is a Keras 3.x model trained specifically to detect malicious SQLs. It is able to detect various SQL injection vectors such as Error-based, Union-based, Blind, Boolean-based
|
36 |
-
,Time-based, Out-of-band, Stacked queries. This was trained on ~167K SQLs containing an almost even distribution of malicious and benign SQLs.
|
37 |
-
SQL with special masking tokens. The training consisted of a warm-up period with a smaller, sinusoidally decaying learning rate
|
38 |
followed by a higher learning rate with cosine decay. A special callback was used to monitor for and protect against gradient
|
39 |
explosions. Weight and kernel constraints are applied to help prevent overfitting and achieve better generalization.
|
40 |
For faster model loading and inference, [mixed precision](https://www.tensorflow.org/guide/mixed_precision) has been used.
|
41 |
|
42 |
-
The best checkpoint
|
43 |
|
44 |
**CONTEXT WINDOW:** 1200 tokens
|
45 |
**PARAMETERS:** 30.7M *(**Trainable:** 7.7M, **Frozen:** 2K, **Optimizer:** 23M)*
|
|
|
33 |
## Overview
|
34 |
|
35 |
This is a Keras 3.x model trained specifically to detect malicious SQLs. It is able to detect various SQL injection vectors such as Error-based, Union-based, Blind, Boolean-based
|
36 |
+
,Time-based, Out-of-band, Stacked queries. This was trained on ~167K SQLs containing an almost even distribution of malicious and benign SQLs. Its training involved preprocessing specifically for
|
37 |
+
SQL with special masking tokens. 28 additional numeric features were also generated and top 10 among them were selected for training using Recursive Feature Elimination. The training consisted of a warm-up period with a smaller, sinusoidally decaying learning rate
|
38 |
followed by a higher learning rate with cosine decay. A special callback was used to monitor for and protect against gradient
|
39 |
explosions. Weight and kernel constraints are applied to help prevent overfitting and achieve better generalization.
|
40 |
For faster model loading and inference, [mixed precision](https://www.tensorflow.org/guide/mixed_precision) has been used.
|
41 |
|
42 |
+
The best checkpoint has been saved and made available for use.
|
43 |
|
44 |
**CONTEXT WINDOW:** 1200 tokens
|
45 |
**PARAMETERS:** 30.7M *(**Trainable:** 7.7M, **Frozen:** 2K, **Optimizer:** 23M)*
|