Malware Classification on Microsoft Malware Classification Challenge

Metric: Macro F1 (10-fold) (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Macro F1 (10-fold)▼	Extra Data	Paper	Date↕	Code
1	HYDRA	0.9951	No	-	-	Code
2	Zhang et al. (2016): Total lines of each Section, Operation Code Count, API Usage, Special Symbols Count, Asm File Pixel Intensity Feature, Bytes File Block Size Distribution, Bytes File N-Gram + Ensemble Learning (XGBoost)	0.9938	No	-	-	Code
3	Ahmadi et al. (2016): ENT, Bytes 1-G, STR, IMG1, IMG2, MD1, MISC, OPC, SEC, REG, DP, API, SYM, MD2 IMG and Opcode N-Grams + Ensemble Learning (XGBoost)	0.9931	No	-	-	Code
4	SEA	0.9908	No	Sequential Embedding-based Attentive (SEA) class...	2023-02-11	Code
5	Orthrus	0.9872	No	-	-	Code
6	Opcode-based Shallow CNN	0.9856	No	-	-	Code
7	Hierarchical Convolutional Network	0.983	No	-	-	-
8	Dynamic Time Wrapping + K-NN	0.9813	No	-	-	Code
9	Autoencoders+Residual Network	0.9719	No	-	-	-
10	Scaled bytes sequence + CNN & Bidirectional LSTM	0.9662	No	-	-	Code
11	Ahmadi et al. (2016): API feature vector + XGBoost	0.9638	No	-	-	Code
12	Multiresolution CNN	0.9636	No	-	-	Code
13	CNN+BiLSTM	0.9605	No	-	-	-
14	Hierarchical Attention Network	0.9468	No	-	-	-
15	Gray-scale IMG CNN	0.94	No	-	-	Code
16	Structural entropy CNN	0.9314	No	-	-	Code
17	Narayanan et al. (2016): PCA features + 1-NN	0.9102	No	-	-	Code
18	DeepConv	0.9071	No	-	-	-
19	MalConv	0.8902	No	-	-	-

#1HYDRA
0.9951
Macro F1 (10-fold)
No paperCode
#2Zhang et al. (2016): Total lines of each Section, Operation Code Count, API Usage, Special Symbols Count, Asm File Pixel Intensity Feature, Bytes File Block Size Distribution, Bytes File N-Gram + Ensemble Learning (XGBoost)
0.9938
Macro F1 (10-fold)
No paperCode
#3Ahmadi et al. (2016): ENT, Bytes 1-G, STR, IMG1, IMG2, MD1, MISC, OPC, SEC, REG, DP, API, SYM, MD2 IMG and Opcode N-Grams + Ensemble Learning (XGBoost)
0.9931
Macro F1 (10-fold)
No paperCode
#4SEASOTA
0.9908
Macro F1 (10-fold)· 2023-02-11
Sequential Embedding-based Attentive (SEA) classifier for malware classification Code
#5Orthrus
0.9872
Macro F1 (10-fold)
No paperCode
#6Opcode-based Shallow CNN
0.9856
Macro F1 (10-fold)
No paperCode
#7Hierarchical Convolutional Network
0.983
Macro F1 (10-fold)
No paper
#8Dynamic Time Wrapping + K-NN
0.9813
Macro F1 (10-fold)
No paperCode
#9Autoencoders+Residual Network
0.9719
Macro F1 (10-fold)
No paper
#10Scaled bytes sequence + CNN & Bidirectional LSTM
0.9662
Macro F1 (10-fold)
No paperCode
#11Ahmadi et al. (2016): API feature vector + XGBoost
0.9638
Macro F1 (10-fold)
No paperCode
#12Multiresolution CNN
0.9636
Macro F1 (10-fold)
No paperCode
#13CNN+BiLSTM
0.9605
Macro F1 (10-fold)
No paper
#14Hierarchical Attention Network
0.9468
Macro F1 (10-fold)
No paper
#15Gray-scale IMG CNN
0.94
Macro F1 (10-fold)
No paperCode
#16Structural entropy CNN
0.9314
Macro F1 (10-fold)
No paperCode
#17Narayanan et al. (2016): PCA features + 1-NN
0.9102
Macro F1 (10-fold)
No paperCode
#18DeepConv
0.9071
Macro F1 (10-fold)
No paper
#19MalConv
0.8902
Macro F1 (10-fold)
No paper