Artificial Intelligence and Security: 6th International Conference, ICAIS 2020, Hohhot, China, July 17–20, 2020, Proceedings, Part I

Malicious software is designed to destroy or occupy the resources of the target computer, which seriously violates the legitimate interests of users. Currently, methods based on static detection have certain limitations to the malicious samples of system call confusion. The existing dynamic detection methods mainly extract features from the local system Application Programming Interface (API) sequence dynamically invoked, and combine them with Random Forests andN-grams, which have limited accuracy for detection results. This paper proposes a weight generation algorithm based on Attention mechanism andmultifeature fusion approach, combined with the advantages of Convolutional Neural Networks (CNN) and Gated Recurrent Unit (GRU) algorithms to learn local features of the API sequence and dependencies and relations among API sequences. The experiment tested eight of the most common types of malware. Experimental results show that the proposed method shows a better work than traditional malware detection model in the research of malware detection based on system API call sequences.

[1]  Yong Gan,et al.  Early SKIP mode decision for three-dimensional high efficiency video coding using spatial and interview correlations , 2014, J. Electronic Imaging.

[2]  Ying Chen,et al.  Overview of the Multiview and 3D Extensions of High Efficiency Video Coding , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[3]  Razvan Pascanu,et al.  Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks , 2013, ECML/PKDD.

[4]  Zhaohong Li,et al.  A HEVC Video Steganalysis Algorithm Based on PU Partition Modes , 2019, Computers, Materials & Continua.

[5]  Keqin Li,et al.  Dual Model Learning Combined With Multiple Feature Selection for Accurate Visual Tracking , 2019, IEEE Access.

[6]  Zulin Wang,et al.  Reducing Complexity of HEVC: A Deep Learning Approach , 2017, IEEE Transactions on Image Processing.

[7]  C.-C. Jay Kuo,et al.  Efficient Multiview Depth Coding Optimization Based on Allowable Depth Distortion in View Synthesis , 2014, IEEE Transactions on Image Processing.

[8]  Nanning Zheng,et al.  A Novel Method of Minimizing View Synthesis Distortion Based on Its Non-Monotonicity in 3D Video , 2017, IEEE Transactions on Image Processing.

[9]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[10]  Chih-Wei Chen,et al.  Efficient inter-prediction depth coding algorithm based on depth map segmentation for 3D-HEVC , 2018, Multimedia Tools and Applications.

[11]  Bin Wang,et al.  CART-based fast CU size decision and mode decision algorithm for 3D-HEVC , 2019, Signal Image Video Process..

[12]  Heiko Schwarz,et al.  3D video coding using the synthesized view distortion change , 2012, 2012 Picture Coding Symposium.

[13]  Wen Gao,et al.  Low Complexity Adaptive View Synthesis Optimization in HEVC Based 3D Video Coding , 2014, IEEE Transactions on Multimedia.

[14]  Fu Li,et al.  Feedback LSTM network based on attention for image description generator , 2019 .

[15]  Yan Zheng,et al.  Truth Discovery on Categorical Multi-Valued Attributes with Source Relations , 2018, 2018 IEEE 4th International Conference on Computer and Communications (ICCC).

[16]  Ying Chen,et al.  Standardized Extensions of High Efficiency Video Coding (HEVC) , 2013, IEEE Journal of Selected Topics in Signal Processing.

[17]  Hui Yuan,et al.  Fine Virtual View Distortion Estimation Method for Depth Map Coding , 2018, IEEE Signal Processing Letters.

[18]  Jack W. Stokes,et al.  Large-scale malware classification using random projections and neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[19]  Hui Li,et al.  SMASH: A Malware Detection Method Based on Multi-Feature Ensemble Learning , 2019, IEEE Access.

[20]  Yaowu Chen,et al.  Hole-filling map-based coding unit size decision for dependent views in three-dimensional high-efficiency video coding , 2016, J. Electronic Imaging.

[21]  Qi Cui Identifying materials of photographic images and photorealistic computer generated graphics based on deep CNNs , 2018 .

[22]  César A. M. Marcon,et al.  Fast 3D-Hevc Depth Maps Intra-Frame Prediction Using Data Mining , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[23]  Baoyu Ma,et al.  A Method for Improving CNN-Based Image Recognition Using DCGAN , 2018 .

[24]  Nanning Zheng,et al.  Efficient Estimation of View Synthesis Distortion for Depth Coding Optimization , 2019, IEEE Transactions on Multimedia.

[25]  Jialie Shen,et al.  Attention-Aware Network With Latent Semantic Analysis for Clothing Invariant Gait Recognition , 2019, Computers, Materials & Continua.

[26]  Yan Li,et al.  Hashtag Recommendation Using LSTM Networks with Self-Attention , 2019, Computers, Materials & Continua.

[27]  Wang Yijie,et al.  Paragraph Vector Representation Based on Word to Vector and CNN Learning , 2018 .

[28]  Nicholas G. Polson,et al.  Deep learning for short-term traffic flow prediction , 2016, 1604.04527.

[29]  Sattar Hashemi,et al.  Malware detection based on mining API calls , 2010, SAC '10.