Malware Classification on Microsoft Malware Classification Challenge

Metric: Accuracy (10-fold) (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Accuracy (10-fold)▼	Extra Data	Paper	Date↕	Code
1	MalConv	9641	No	-	-	-
2	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)	0.9976	No	-	-	Code
3	HYDRA	0.9975	No	-	-	Code
4	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)	0.9974	No	-	-	Code
5	Orthrus	0.9924	No	-	-	Code
6	Opcode-based Shallow CNN	0.9917	No	-	-	Code
7	Hierarchical Convolutional Network	0.9913	No	-	-	-
8	SEA	0.9912	No	Sequential Embedding-based Attentive (SEA) class...	2023-02-11	Code
9	Dynamic Time Wrapping + K-NN	0.9894	No	-	-	Code
10	Ahmadi et al. (2016): API feature vector + XGBoost	0.9868	No	-	-	Code
11	Autoencoders+Residual Network	0.9861	No	-	-	-
12	Multiresolution CNN	0.9828	No	-	-	Code
13	CNN+BiLSTM	0.982	No	-	-	-
14	Scaled bytes sequence + CNN & Bidirectional LSTM	0.9814	No	-	-	Code
15	Grayscale images + Opcode N-grams (Feature selection for malware classification)	0.977	No	-	-	Code
16	DeepConv	0.9756	No	-	-	-
17	Gray-scale IMG CNN	0.975	No	-	-	Code
18	Hierarchical Attention Network	0.9742	No	-	-	-
19	Structural entropy CNN	0.9708	No	-	-	Code
20	Narayanan et al. (2016): PCA features + 1-NN	0.966	No	-	-	Code
21	Deep Transferred Generative Adversarial Networks	0.9639	No	-	-	Code
22	Zero Rule Classifier	0.2707	No	-	-	Code
23	Random Guess Classifier	0.1755	No	-	-	Code

#1MalConv
9641
Accuracy (10-fold)
No paper
#2Ahmadi 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)
0.9976
Accuracy (10-fold)
No paperCode
#3HYDRA
0.9975
Accuracy (10-fold)
No paperCode
#4Zhang 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)
0.9974
Accuracy (10-fold)
No paperCode
#5Orthrus
0.9924
Accuracy (10-fold)
No paperCode
#6Opcode-based Shallow CNN
0.9917
Accuracy (10-fold)
No paperCode
#7Hierarchical Convolutional Network
0.9913
Accuracy (10-fold)
No paper
#8SEASOTA
0.9912
Accuracy (10-fold)· 2023-02-11
Sequential Embedding-based Attentive (SEA) classifier for malware classification Code
#9Dynamic Time Wrapping + K-NN
0.9894
Accuracy (10-fold)
No paperCode
#10Ahmadi et al. (2016): API feature vector + XGBoost
0.9868
Accuracy (10-fold)
No paperCode
#11Autoencoders+Residual Network
0.9861
Accuracy (10-fold)
No paper
#12Multiresolution CNN
0.9828
Accuracy (10-fold)
No paperCode
#13CNN+BiLSTM
0.982
Accuracy (10-fold)
No paper
#14Scaled bytes sequence + CNN & Bidirectional LSTM
0.9814
Accuracy (10-fold)
No paperCode
#15Grayscale images + Opcode N-grams (Feature selection for malware classification)
0.977
Accuracy (10-fold)
No paperCode
#16DeepConv
0.9756
Accuracy (10-fold)
No paper
#17Gray-scale IMG CNN
0.975
Accuracy (10-fold)
No paperCode
#18Hierarchical Attention Network
0.9742
Accuracy (10-fold)
No paper
#19Structural entropy CNN
0.9708
Accuracy (10-fold)
No paperCode
#20Narayanan et al. (2016): PCA features + 1-NN
0.966
Accuracy (10-fold)
No paperCode
#21Deep Transferred Generative Adversarial Networks
0.9639
Accuracy (10-fold)
No paperCode
#22Zero Rule Classifier
0.2707
Accuracy (10-fold)
No paperCode
#23Random Guess Classifier
0.1755
Accuracy (10-fold)
No paperCode