Malware Classification

Malware Classification is the process of assigning a malware sample to a specific malware family. Malware within a family shares similar properties that can be used to create signatures for detection and classification. Signatures can be categorized as static or dynamic based on how they are extracted. A static signature can be based on a byte-code sequence, binary assembly instruction, or an imported Dynamic Link Library (DLL). Dynamic signatures can be based on file system activities, terminal commands, network communications, or function and system call sequences.

Source: Behavioral Malware Classification using Convolutional Recurrent Neural Networks

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 141–146 of 146 papers

Title	Date	Tasks	Status
Integration of Static and Dynamic Analysis for Malware Family Classification with Composite Neural Network	Dec 24, 2019	ClassificationGeneral Classification	CodeCode Available
Adversarial Robustness with Non-uniform Perturbations	Feb 24, 2021	Adversarial RobustnessMalware Classification	CodeCode Available
Towards Building an Intelligent Anti-Malware System: A Deep Learning Approach using Support Vector Machine (SVM) for Malware Classification	Dec 31, 2017	General ClassificationMalware Classification	CodeCode Available
KiloGrams: Very Large N-Grams for Malware Classification	Aug 1, 2019	ClassificationGeneral Classification	CodeCode Available
Sequential Embedding-based Attentive (SEA) classifier for malware classification	Feb 11, 2023	ClassificationMalware Classification	CodeCode Available
Learning a Neural-network-based Representation for Open Set Recognition	Feb 12, 2018	General ClassificationMalware Classification	CodeCode Available

Show:10 25 50

← PrevPage 15 of 15Next →

All datasets Microsoft Malware Classification Challenge Malimg Dataset MaleVis

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	MalConv	Accuracy (10-fold)	9,641	—	Unverified
2	TPOT Classifier	Accuracy (5-fold)	98.94	—	Unverified
3	CNN BiLSTM - Reb Sampl	Accuracy (5-fold)	98.2	—	Unverified
4	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)	Accuracy (10-fold)	1	—	Unverified
5	HYDRA	Accuracy (10-fold)	1	—	Unverified
6	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)	Accuracy (10-fold)	1	—	Unverified
7	Orthrus	Accuracy (10-fold)	0.99	—	Unverified
8	Opcode-based Shallow CNN	Accuracy (10-fold)	0.99	—	Unverified
9	Hierarchical Convolutional Network	Accuracy (10-fold)	0.99	—	Unverified
10	SEA	Accuracy (10-fold)	0.99	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GA Designed Deep CNN	Accuracy	0.99	—	Unverified
2	Gray-scale IMG CNN	Accuracy (10-fold)	0.98	—	Unverified
3	GRU + SVM	Accuracy	0.85	—	Unverified
4	FFNN + SVM	Accuracy	0.8	—	Unverified
5	CNN + SVM	Accuracy	0.77	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Levit-MC	Accuracy	96.6	—	Unverified