An Xception Convolutional Neural Network for Malware Classification with Transfer Learning
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
In this work, we applied a deep Convolutional Neural Network (CNN) with Xception model to perform malware image classification. The Xception model is a recently developed special CNN architecture that is more powerful with less over- fitting problems than the current popular CNN models such as VGG16. However only a few use cases of the Xception model can be found in literature, and it has never been used to solve the malware classification problem. The performance of our approach was compared with other methods including KNN, SVM, VGG16 etc. The experiments on two datasets (Malimg and Microsoft Malware Dataset) demonstrated that the Xception model can achieve the highest training accuracy than all other approaches including the champion approach, and highest validation accuracy than all other approaches including VGG16 model which are using image-based malware classification (except the champion solution as this information was not provided). Additionally, we proposed a novel ensemble model to combine the predictions from .bytes files and .asm files, showing that a lower logloss can be achieved. Although the champion on the Microsoft Malware Dataset achieved a bit lower logloss, our approach does not require any features engineering, making it more effective to adapt to any future evolution in malware, and very much less time consuming than the champion's solution.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Conversely, the suggested Xception transformation approach achieves extra learning efficiency and better performance but does not minimize the number of parameters [126, 127].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [126]
Citations
Cites
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380 · cited 1×
“The Xception model [14] was proposed by Google, Inc.”
MethodXception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2016) · arXiv · doi:10.48550/arxiv.1610.02357 · Cited by 538 · cited 1×
“The Xception model [14] was proposed by Google, Inc.”
MethodMalware Classification with Deep Convolutional Neural Networks
Kalash, M., Rochan, M., Mohammed, N., Bruce, N. D. B., Wang, Y., & Iqbal, F. (2018) · 2018 9th IFIP International Conference on New Technologies, Mobility and Security (NTMS) · doi:10.1109/ntms.2018.8328749 · Cited by 408 · cited 2×
“The experiments results demonstrate that the validation accuracy of the Xception model on the Malimg Dataset [8] and the Microsoft malware datasets [9] is higher (99.”
MethodSelf-citationMicrosoft Malware Classification ChallengePreprint
Ronen, R., Radu, M., Feuerstein, C., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.10135 · Cited by 287 · cited 1×
“Microsoft Malware Dataset The Microsoft Malware Dataset [15] was released by the Kaaggle Microsoft Malware Classification Competition.”
MethodMicrosoft Malware Classification Challenge
Ronen, R., Radu, M., Feuerstein, C., Yom‐Tov, E., & Ahmadi, M. (2018) · arXiv (Cornell University) · doi:10.13140/rg.2.2.34695.91045 · Cited by 286
Malware images: visualization and automatic classification
Nataraj (2011) · (No Title) · Cited by 215
Visual Reverse Engineering of Binary and Data Files
Conti, G., Dean, E., Sinda, M., & Sangster, B. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85933-8_1 · Cited by 93 · cited 1×
“[17] visualized the raw binary data of primitive binary fragments (such as text, C++ data structures, image data, and video data) into the images.”
BackgroundMalware Images Classification Using Convolutional Neural Network
Kabanga, E. K., & Kim, C. (2017) · Journal of Computer and Communications · doi:10.4236/jcc.2018.61016 · Cited by 70
Classification of malware families based on N-grams sequential pattern features
-, C. L., & Sornil, O. (2013) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2013.6566472 · Cited by 61 · cited 2×
“Nowadays, most antivirus vendors have used machine learning to solve this problem and applied these techniques throughout the industry, for example using statistical characteristics like API calls [4] or N-grams [5].”
MethodPolymorphic malware detection using sequence classification methods and ensembles
Drew, J. M., Hahsler, M., & Moore, T. (2017) · EURASIP Journal on Information Security · doi:10.1186/s13635-017-0055-6 · Cited by 59 · cited 1×
“Strand Gene Sequence [18] .”
Research works printed but not linked: 8
- lin, 2013, Network in Network
- makandar, 2015, Malware Image Analysis and Classification using Support Vector Machine, International Journal of Advanced Trends in Computer Science and Engineering, 4, 1
- team, 2015, Microsoft Malware Winners’ Interview 1st place ‘NO to overfitting! - Confusion matrix’ | No Free Hunch
- li, 2017, CS231 Lecture 09? CNN Architectures, 1
- 2017, How Traditional Antivirus Works
- 2018, Documentation for individual models
- 2017, Kaspersky Lab detects 360 000 new malicious files daily – up 11 5% from 2016
- robert moir, 2003, Defining Malware
Cited by
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
MobileNet Based Apple Leaf Diseases Identification
Bi, C., Wang, J., Duan, Y., Fu, B., Kang, J.-R., & Shi, Y. (2022) · Mobile Networks and Applications · doi:10.1007/s11036-020-01640-1 · Cited by 256
“Lo et al. [24] applied a deep CNN with Xception model to perform malware image classification, with a validation accuracy as high as 99.17%.”
MethodInfluentialMulti-Level Deep Learning Model for Potato Leaf Disease Recognition
Rashid, J., Khan, I., Ali, G., Almotiri, S. H., AlGhamdi, M. A., & Masood, K. (2021) · Electronics · doi:10.3390/electronics10172064 · Cited by 237
“To evaluate the performance of the proposed PDDCNN model, we performed transferred learning on VGG16 [31], InceptionResNetV2 [45], DenseNet_121 [46], DenseNet169 [46] and Xception [47] models with the proposed PDDCNN model on the PLD dataset.”
MethodResultInfluentialA novel deep learning-based approach for malware detection
Shaukat, K., Luo, S., & Varadharajan, V. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106030 · Cited by 209
Shaheed, K., Mao, A., Qureshi, I., Kumar, M., Hussain, S., Ullah, I., & Zhang, X. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.116288 · Cited by 168
A survey of malware detection using deep learning
Bensaoud, A., Kalita, J. K., & Bensaoud, M. (2024) · Machine Learning with Applications · doi:10.1016/j.mlwa.2024.100546 · Cited by 220
Sudhakar, & Kumar, S. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.06.029 · Cited by 139
Performance Comparison of Deep CNN Models for Detecting Driver’s Distraction
Srinivasan, K., Garg, L., Datta, D., Alaboudi, A. A., Jhanjhi, N. Z., Agarwal, R., & Thomas, A. G. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2021.016736 · Cited by 118
Fusing feature engineering and deep learning: A case study for malware classification
Gibert, D., Planes, J., Mateu, C., & Le, Q. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117957 · Cited by 106
Zhu, J., Jang‐Jaccard, J., Singh, A. S. G., Welch, I. S., Al-Sahaf, H., & Camtepe, S. A. (2022) · Computers & Security · doi:10.1016/j.cose.2022.102691 · Cited by 92
“In the same vein, Lo et al. [9] employed pre-trained weights from Xception neural network with malware classification.”
Chaganti, R., Ravi, V., & Pham, T. D. (2022) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2022.103306 · Cited by 113
Atitallah, S. B., Driss, M., & Almomani, I. (2022) · Sensors · doi:10.3390/s22114302 · Cited by 88
Ahmad, N., Shah, J. H., Khan, M. A., Baili, J., Ansari, G. J., Tariq, U., Kim, Y. J., & Cha, J. (2023) · Frontiers in Oncology · doi:10.3389/fonc.2023.1151257 · Cited by 93
“Among all, except for the fi rst and last modules, the 36 convolutional layers are organized into 14 modules, each of which is surrounded by linear residual connections (49).”
BackgroundJena, B., Nayak, G. K., & Saxena, S. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6767 · Cited by 85
Moreira, C. C., Moreira, D. C., & Sales, C. (2023) · Computers & Security · doi:10.1016/j.cose.2023.103265 · Cited by 77
A novel machine learning approach for detecting first-time-appeared malware
Shaukat, K., Luo, S., & Varadharajan, V. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107801 · Cited by 71
Real-time driver distraction recognition: A hybrid genetic deep network based approach
Aljohani, A. A. (2022) · Alexandria Engineering Journal · doi:10.1016/j.aej.2022.12.009 · Cited by 63
Metamorphic Malware and Obfuscation: A Survey of Techniques, Variants, and Generation Kits
Brezinski, K., & Ferens, K. (2023) · Security and Communication Networks · doi:10.1155/2023/8227751 · Cited by 80
Graph Neural Network-based Android Malware Classification with Jumping Knowledge
Lo, W. W., Layeghy, S., Sarhan, M., Gallagher, M. R., & Portmann, M. (2022) · IEEE Conference on Dependable and Secure Computing (DSC) · doi:10.1109/dsc54232.2022.9888878 · Cited by 64
“[15][16][17] convert malware samples as grayscale images then fed them to the CNNs for malware detection and classification.”
MethodSelf-citationResNeXt+: Attention Mechanisms Based on ResNeXt for Malware Detection and Classification
He, Y., Kang, X., Yan, Q., & Li, E. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3328431 · Cited by 48
“Typical deep learning methods are based on VGG16 [15], Xception [16], Resnet [17], [18], CNN + LSTM [19], Desnet [20], AE-DCNN [21], the introduction of these methods has greatly accelerated the progress of malware classification.”
MethodMalware classification with Word2Vec, HMM2Vec, BERT, and ELMo
Kale, A. S., Pandya, V., Troia, F. D., & Stamp, M. (2022) · Journal of Computer Virology and Hacking Techniques · doi:10.1007/s11416-022-00424-3 · Cited by 47
“In [13], the authors consider an ensemble model that combines predictions from asm and exe , files together—the predictions are stacked and fed to a neural network for classification.”
BackgroundImage segmentation using transfer learning and Fast R-CNN for diabetic foot wound treatments
Huang, H., Zhang, T., Yang, C., Sheen, Y., Chen, H., Chen, C.-J., & Tseng, M.-W. (2022) · Frontiers in Public Health · doi:10.3389/fpubh.2022.969846 · Cited by 54
Hossain, M. M., Hasan, M. M., Rahim, M. A., Rahman, M. M., Yousuf, M. A., Al-Ashhab, S., Akhdar, H., Alyami, S. A., Azad, A., & Moni, M. A. (2022) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2022.3197923 · Cited by 49
“After setting x i and v i for each p i , the proposed CNN model is executed for every p i Xception [18], and vanilla CNN baseline [48] because of providing contextual outcomes.”
MethodTransfer Learning for Image-Based Malware Detection for IoT
Panda, P., Kumar, C. U. O., Marappan, S., Suresh, M., Manimurugan, S., & Nandi, D. V. (2023) · Sensors · doi:10.3390/s23063253 · Cited by 51
“The S-DCNN model used in [51] and Experiment 2 (80:20) with our SE-AGM model had the same accuracy value of 99.”
MethodInfluentialKumar, S., & Panda, K. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110676 · Cited by 43
Rahman, W., Hossain, M. M., Hasan, M. M., Iqbal, M. S., Rahman, M. M., Hasan, K. F., & Moni, M. A. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3394799 · Cited by 42
“By analyzing several CNN techniques, namely VGG19 [32], VGG16 [33], ResNet50 [34], InceptionV3 [35], and Xception [36], because of providing excellent outcomes, VGG19 is selected to build the final approach for this research.”
MethodRNN-CNN Based Cancer Prediction Model for Gene Expression
Thakur, T., Batra, I., Malik, A., Ghimire, D., Kim, S., & Hosen, A. S. M. S. (2023) · IEEE Access · doi:10.1109/access.2023.3332479 · Cited by 42
“…Function: The cross-entropy loss function with soft-max activation can be defined as per equation (4): where, y true , i is the true label for class i . y pred , i is the predicted value for class i • VGG-16: VGG-16, being one of the popular CNN models, is used for classification of images [52].”
MethodZhang, D., Song, Y., Xiang, Q., & Wang, Y. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.10.055 · Cited by 42
Self-citationAutomatic guava disease detection using different deep learning approaches
Tewari, V., Azeem, N. A., & Sharma, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15909-6 · Cited by 41
Concrete spalling detection system based on semantic segmentation using deep architectures
Yasmin, T., La, D., La, K. T., Nguyễn, M. T., & La, H. M. (2024) · Computers & Structures · doi:10.1016/j.compstruc.2024.107398 · Cited by 32
AlMohimeed, A., Saleh, H., El-Rashidy, N. M., Saad, R. M. A., El–Sappagh, S., & Mostafa, S. (2023) · Diagnostics · doi:10.3390/diagnostics13111968 · Cited by 34
“Depthwise separable convolution layers are based on the principle that convolutional neural network feature maps resulting from such cross-channel and spatial correlation translation could be entirely independent [71].”
BackgroundBhardwaj, S., Li, A. S., Dave, M., & Bertino, E. (2024) · Computers & Security · doi:10.1016/j.cose.2024.103769 · Cited by 29
Exploring Optimal Deep Learning Models for Image-based Malware Variant Classification
Mitsuhashi, R., & Shinagawa, T. (2022) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac54236.2022.00128 · Cited by 32
Multimodal malware classification using proposed ensemble deep neural network framework
Nazim, S., Alam, M. M., Rizvi, S. S. A., Mustapha, J. C., Hussain, S. S., & Su’ud, M. M. (2025) · Scientific Reports · doi:10.1038/s41598-025-96203-3 · Cited by 27
Classification of bread wheat varieties with a combination of deep learning approach
Yaşar, A., Gölcük, A., & Sari, O. F. (2023) · European Food Research and Technology · doi:10.1007/s00217-023-04375-x · Cited by 26
“Except for the first and last modules of the 36 convolution layers, there are 14 linear jump modules around all of them [42].”
Kallel, I. F., Mahfoudhi, O., & Kammoun, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17551-8 · Cited by 25
“…transfer learning models VGG19, ResNet50, Xception, and MobileNetV2, have been proven with remarkably high performance in several applications [47, 48] it can be noticed that these models perform comparably to the smaller and simpler convolutional models such as the customised classic CNN and…”
Automatic Estuarine Fish Species Classification System Based on Deep Learning Techniques
Tejaswini, H., Pai, M. M. M., & Pai, R. M. (2024) · IEEE Access · doi:10.1109/access.2024.3468438 · Cited by 23
Abdulazeez, F. A., Ahmed, I. T., & Hammad, B. T. (2024) · Applied Sciences · doi:10.3390/app14062614 · Cited by 25
Singh, S., Krishnan, D., Vazirani, V., Ravi, V., & Alsuhibany, S. A. (2024) · Egyptian Informatics Journal · doi:10.1016/j.eij.2024.100539 · Cited by 22
A Transfer Learning Approach for Predicting Alzheimer's Disease
Rajeswari, S. S., & Nair, M. (2021) · Biennial International Conference on Nascent Technologies in Engineering (ICNTE) · doi:10.1109/icnte51185.2021.9487746 · Cited by 24
Ferdous, J., Islam, R., Mahboubi, A., & Islam, M. Z. (2025) · Scientific Reports · doi:10.1038/s41598-025-17647-1 · Cited by 21
“16,18,51,56 .”
Green Space Quality Analysis Using Machine Learning Approaches
Rustamov, J., Rustamov, Z., & Zaki, N. (2023) · Sustainability · doi:10.3390/su15107782 · Cited by 19
MalNet: A Large-Scale Cybersecurity Image Database of Malicious SoftwarePreprint
Freitas, S., Duggal, R., & Chau, D. H. (2021) · arXiv (Cornell University) · Cited by 19
Image Classification Based on Light Convolutional Neural Network Using Pulse Couple Neural Network
Rafidison, M. A., Malalatiana, R. H., Randriamitantsoa, P. A., Rafanantenana, S. H. J., Toky, R. F. M., Rakotondrazaka, L. P., & Rakotomihamina, A. H. (2023) · Computational Intelligence and Neuroscience · doi:10.1155/2023/7371907 · Cited by 16
“Te threshold is dynamic in that when the neuron fres (Y>Θ) the threshold then signifcantly increases its value [23].”
BackgroundMethodMalware Classification with Word Embedding Features
Kale, A. S., Troia, F. D., & Stamp, M. (2021) · International Conference on Information Systems Security and Privacy (ICISSP) · doi:10.5220/0010377907330742 · Cited by 16
“In (Lo et al., 2019), the authors consider an ensemble model that combines predictions from asm and exe , files together—the predictions are stacked and fed to a neural network for classification.”
BackgroundGibert, D., Totosis, N., Patsakis, C., Le, Q., & Zizzo, G. (2025) · Computers & Security · doi:10.1016/j.cose.2025.104495 · Cited by 15
Rashid, H., Benbouzid, M., Amirat, Y., Berghout, T., Titah-Benbouzid, H., & Mamoune, A. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109316 · Cited by 15
Leveraging Transfer Learning for Accurate Detection of Diseases in Rice Leaf Images
Ali, M. H., Mahmud, T., Mim, S. J., Aziz, M. T., Hossain, M. S., & Andersson, K. (2024) · IEEE International Conference on Computing, Applications and Systems (COMPAS) · doi:10.1109/compas60761.2024.10796309 · Cited by 15
“Next, in order to identify the malware photos, the new softmax layer was trained using the bottleneck characteristics [40], [41].”
Self-supervised contrastive representation learning for classifying Internet of Things malware
Wang, F., Chen, Y., Gao, H., Li, Q., & Wang, C. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110299 · Cited by 14
Lanjewar, M. G., Shaikh, A. Y., & Parab, J. S. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-14232-w · Cited by 15
“Xception architecture achieves better learning efficiency but cannot reduce the number of training parameters [38, 55].”
BackgroundManta Ray Foraging Optimization with Transfer Learning Driven Facial Emotion Recognition
Hilal, A. M., Elkamchouchi, D. H., Alotaibi, S. S., Maray, M., Othman, M., Abdelmageed, A. A., Zamani, A. S., & Eldesouki, M. I. (2022) · Sustainability · doi:10.3390/su142114308 · Cited by 15
Comparative Analysis of Imbalanced Malware Byteplot Image Classification Using Transfer Learning
Jayasudha, M., Shaik, A., Pendharkar, G., Kumar, S., Kumar, B. M., & Balaji, S. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-7216-6_26 · Cited by 13
“The high accuracy is commendable but the usage of accuracy as the primary metric can be misleading on the actual nature of the model.[7] Singh, A.”
BackgroundNagib, A. E., Mohamed, H. C., & Ashraf, A. (2023) · Intelligent Methods, Systems, and Applications (IMSA) · doi:10.1109/imsa58542.2023.10217616 · Cited by 12
“The Xception model is a developed special CNN architecture that is more powerful with less overfitting problems than some popular CNN models such as VGG16 [9].”
MethodRadon transform based malware classification in cyber-physical system using deep learning
Alguliyev, R. M., Aliguliyev, R. M., & Sukhostat, L. V. (2024) · Results in Control and Optimization · doi:10.1016/j.rico.2024.100382 · Cited by 18
Detection of driver drowsiness using transfer learning techniques
Mate, P., Apte, N., Parate, M., & Sharma, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16952-z · Cited by 10
“Xception models have been used for malware image classification problems with the use of Transfer Learning [26].”
Implementation of an Attention Mechanism Model for Facial Beauty Assessment Using Transfer Learning
Yang, C., Wang, Y.-C., Lo, L., Chiang, W.-C., Kuang, S.-K., & Lin, H. (2023) · Diagnostics · doi:10.3390/diagnostics13071291 · Cited by 10
“In 2018, Google again proposed two language models, BERT and GPT, making the attention mechanism a popular research avenue.”
MethodInfluentialSelf-citationOnoja, M., Jegede, A., Blamah, N. V., Olawale, A. V., & Omotehinwa, T. O. (2022) · Journal of Computing and Social Informatics · doi:10.33736/jcsi.4739.2022 · Cited by 12
“A study by Lo et al. (2019) classified malware into families based on the integration of deep CNN with Xception model.”
MethodDo you “like” my tweets? Exploring verbal and visual cues in traveler’s dual-coding process
Luo, Y., Zheng, J., Tang, L. R., Wang, X., & Yang, L. (2025) · Journal of Travel & Tourism Marketing · doi:10.1080/10548408.2025.2455436 · Cited by 9
“Do et al., 2019; Lo et al., 2019; Tan et al., 2020).”
Convolutional Neural Network Based IOT Intrusion Detection System using Edge-IIoTset
Singh, M., & Chauhan, N. (2024) · International Conference on Integrated Circuits, Communication, and Computing Systems (ICIC3S) · doi:10.1109/icic3s61846.2024.10603309 · Cited by 9
“Architecture of CNN[14]. comparison between CNN, VGG16, and Xception reveals distinct architectural features.”
BackgroundDudekula, U., & Purnachand, N. (2023) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v30.i1.pp598-605 · Cited by 8
Kumar, S., & Bhowmik, B. R. (2025) · Methods · doi:10.1016/j.ymeth.2025.04.008 · Cited by 7
Explainable machine learning-based cybersecurity detection using LIME and Secml
Alodibat, S., Ahmad, A., & Azzeh, M. (2023) · IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT) · doi:10.1109/jeeit58638.2023.10185893 · Cited by 7
“To increase the probability, analysts must be given signs of penetration related to network occurrences that define the potential threat for analysis [9].”
BackgroundDhar, S., Vishwakarma, A., Ghanti, D., & Jana, N. D. (2022) · IEEE Conference on Information and Communication Technology (CICT) · doi:10.1109/cict56698.2022.9997819 · Cited by 7
“In this work a comparative study is also presented in terms of classification accuracy obtained by considering deep convolutional features from three pre-trained DCNN models such as VGG-16 , VGG-19 and Xception model.”
MethodInfluentialMultistep Machine Learning Pipeline For Polymeric Nanoparticle Design
Fonseca, R., de Santana, I. A., Lima, A. L., Gross, I. P., Gratieri, T., Gelfuso, G. M., & Filho, M. C. (2025) · AAPS PharmSciTech · doi:10.1208/s12249-025-03248-8 · Cited by 6
“Combining these metrics offers a robust framework for evaluating complex multiclassification models, balancing precision and reliability [45, 49].”
Malware image classification: comparative analysis of a fine-tuned CNN and pre-trained models
Majhi, S. K., Panda, A., Srichandan, S. K., Desai, U., & Acharya, B. (2023) · International Journal of Computers and Applications · doi:10.1080/1206212x.2023.2270804 · Cited by 6
Bubble defect detection for tire shearography images with transfer learning based deep CNN models
Saleh, N. A. A., Al-Areqi, F., Konyar, M. Z., Kaplan, K., Öngir, S., & Ertunç, H. M. (2024) · Engineering Research Express · doi:10.1088/2631-8695/ad915b · Cited by 7
Advancing palm oil fruit ripeness classification using transfer learning in deep neural networks
Kurniawan, R., Samsuryadi, S., Mohamad, F. S., Wijaya, H. O. L., & Santoso, B. (2025) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v14i2.8651 · Cited by 5
An Adaptable Ensemble Architecture for Malware Detection
Mane, D., Kumbharkar, P. B., Javheri, S. B., & Moorthy, R. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-3071-2_53 · Cited by 5
Identification of Black Fungus Diseases Using CNN and Transfer-Learning Approach
Hasan, M. I., Mahbub, N. I., & Sarkar, B. (2022) · International Conference on Computing Advancements (ICCA) · doi:10.1145/3542954.3542972 · Cited by 5
“The Xception model utilized depth-wise separable convolution, which has the potential to dramatically lower the cost of the convolution operation [29].”
MethodA hybrid deep learning based robust framework for cattle identification
Gunda, V. S. P., Gulla, H., Kosana, V., & Janapati, S. (2022) · International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC) · doi:10.1109/assic55218.2022.10088414 · Cited by 5
“Xception is a deep learning network made up of 71 layers using over one million images [15].”
BackgroundIMCSCL: Image-Based Malware Classification using Self-Supervised and Contrastive Learning
Jia, Y., Meng, Y., & Zhuang, H. (2023) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs60937.2023.00071 · Cited by 7
“We selected five representative image-based malware detection models[35]–[39] for comparison with IMCSCL.”
MethodPE Parser: A Python package for Portable Executable files processing
Gibert, D. (2022) · Software Impacts · doi:10.1016/j.simpa.2022.100365 · Cited by 5
Balaji, M. A., Venkatesh, S. N., Sugumaran, V., & Ramachandran, K. I. (2025) · Journal of Engineering · doi:10.1155/je/4707723 · Cited by 4
“In this study, the following models were assessed: AlexNet [28], GoogLe-Net [29], ResNet50 [30], VGG16 [31], VGG19 [32], ResNet101 [33], DenseNet [34], Inception-V3 [35], Xcep-tion [36], MobileNet [37], ResNet18 [38], and Shu ffl eNet [39].”
InfluentialDeriving optimal deep learning models for image-based malware classification
Mitsuhashi, R., & Shinagawa, T. (2022) · ACM Symposium on Applied Computing · doi:10.1145/3477314.3507242 · Cited by 4
Malware Classification with Word Embedding FeaturesPreprint
Kale, A. S., Troia, F. D., & Stamp, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02711 · Cited by 4
“In (Lo et al., 2019), the authors consider an ensemble model that combines predictions from asm and exe , files together—the predictions are stacked and fed to a neural network for classification.”
BackgroundConcrete section segmentation with advanced deep learning models and refined labeling approaches
Mesfin, W. M., Kim, G., & Kim, H.-K. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127697 · Cited by 4
Bimodal Emotion Recognition using Machine Learning
Manisha, S., Nafisa, H. S., Gopal, N., & Anand, R. P. (2021) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.d2451.0410421 · Cited by 4
Comparison of Garbage Classification Frameworks Using Transfer Learning and CNN
Gourisaria, M. K., Agrawal, R., Singh, V., Sahni, M., & Raja, L. (2022) · International Journal of Social Ecology and Sustainable Development · doi:10.4018/ijsesd.313973 · Cited by 3
Local Rose Breeds Detection System Using Transfer Learning Techniques
Farha, A. B., Hakim, M. A., & Khatun, M. E. (2022) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt54827.2022.9984329 · Cited by 3
“On the other hand, Xception does not instigate any non-linearity.”
InfluentialMachine Learning Methodologies for Preventing Malware Obfuscation
Carletti, V., Saggese, A., Foggia, P., Greco, A., & Vento, M. (2022) · Internet of things · doi:10.1007/978-3-031-21940-5_6 · Cited by 3
Quality Assessment Assistance of Lateral Knee X-rays: A Hybrid Convolutional Neural Network Approach
Lysdahlgaard, S., Šegota, S. B., Hess, S., Antulov, R., Kusk, M. W., & Car, Z. (2023) · Mathematics · doi:10.3390/math11102392 · Cited by 3
Beef Image Classification Using the Inception V3 Transfer Learning Model
Susanti, E., Cahyo, E. N., Sutanta, E., Ariyana, R. Y., & Kumalasanti, R. A. (2023) · IEEE Information Technology International Seminar (ITIS) · doi:10.1109/itis59651.2023.10420013 · Cited by 3
“Research by [13] with CNN with the Xception model Evaluation compares the model's performance with other methods, namely KNN, Support Vector Machine (SVM), and VGG16.”
MethodEVMNet: Classification of DDoS Attacks using ELM-Enhanced Deep Learning Model with Feature Fusion
Ambekar, N. G., Samal, S., Thokchom, S., & Yogita, Y. (2023) · IEEE India Conference · doi:10.1109/indicon59947.2023.10440676 · Cited by 4
Pre-Trained Deep Learning Models for Malware Image Based Classification and Detection
ghabri, N. E., Belmekki, E., & Bellafkih, M. (2024) · International Conference on Intelligent Computing in Data Sciences (ICDS) · doi:10.1109/icds62089.2024.10756501 · Cited by 3
“It has also been effectively used in image classification [14].”
Transfer Öğrenme Modelleri ile Elma Yapraklarında Hastalık Tespiti
Aybar, M., Talaş, U., & Çubukçu, B. (2024) · Eskişehir Türk Dünyası Uygulama ve Araştırma Merkezi Bilişim Dergisi · doi:10.53608/estudambilisim.1556425 · Cited by 3
Predicting the Breed of Dogs and Cats with Fine-Tuned Keras Applications
Wang, I.-H., Mahardi, Lee, K.-C., & Chang, S. (2021) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2021.019020 · Cited by 3
Enhancing ransomware detection using Siamese network
(2024) · ARPN Journal of Engineering and Applied Sciences · doi:10.59018/022438 · Cited by 2
“The idea of converting one-dimensional data into two-dimensional data to detect and classify malicious ], [27], [28] and [29].”
BackgroundMethodCervical Cancer Classification From Pap Smear Using XCeption Model
Maesaroh, I. S., Syaja’ah, K. N., Perkasa, Y. S., Hadianti, S., Riana, D., & Nurmalasari, R. R. (2024) · International Conference on Wireless and Telematics (ICWT) · doi:10.1109/icwt62080.2024.10674721 · Cited by 2
“The xception model is widely used for image data classification, such as essential oil plant image classification[17], malware classification with transfer learning[18], EEG-based emotion classification[19], breast cancer histology classification[20], and diabetic retinopathy classification[21].”
MethodBhagirath, S. N., Bhatnagar, V., Raja, L., & Kumar, K. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-96-2182-8_21 · Cited by 2
Zhang, T., Yang, C., Lin, H., Lo, L., & Chan, Y.-W. (2020) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-5959-4_3 · Cited by 2
Lin, H., Zhang, T., Wang, Y.-C., Yang, C., Lo, L., Liao, C.-H., & Kuang, S.-K. (2022) · The Journal of Supercomputing · doi:10.1007/s11227-022-04502-7 · Cited by 3
“The parameters, or the combination of the two models can be used in collaboration in practical applications [24, 25].”
BackgroundSelf-citationBuhawe, M. A. A., Rejuso, A. L. M., & Maderazo, C. V. (2022) · International Conference on Information Technology and Digital Applications (ICITDA) · doi:10.1109/icitda55840.2022.9971354 · Cited by 2
“Excluding the first and last modules, all of the 14 modules composed of the 36 convolutional layers have linear skip connections surrounding them [33].”
BackgroundCost-Effective Malware Classification Based on Deep Active Learning
Qian, Q., Chen, Y., Hu, Y., Zang, T., Cheng, M., Pan, Q., Ding, Y., & Qi, Z. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-25538-0_12 · Cited by 2
Sparsely Supervised Learning for Medical Image Classification on Noisy Heterogeneous Data
Thillai Manjari, T., Chakravarthi, S. S., Sountharrajan, S., Rao, B. N. K., Suganya, E., & Nivaashini, M. (2023) · International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) · doi:10.1109/icacite57410.2023.10183290 · Cited by 2
“Transfer learning approach [16] is where a machine uses prior task information to increase generalization about another task.”
BackgroundScreening of Baggage X-ray Images Using Convolutional Neural Networks
Sara, D., & Mandava, A. K. (2023) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit59222.2023.10205696 · Cited by 2
“For performance evaluation of the classification task, accuracy, precision, recall, true positive rate, false positive rate, feature extraction time, prediction time are evaluated for pre-trained CNN models like Resnet, Densenet201 [15], InceptionV3 [16], Googlenet [4], Squeezenet [17], VGG16, VGG19, Alexnet, Inceptio…”
MethodInfluentialDeep Facial Expression Recognition Using Xception Model
Ouhammou, M., Ababou, N., Baslam, M., & Aouragh, S. L. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-80438-0_16 · Cited by 2
Context Dependent Sentiments Analysis Using Machine Learning
Pandey, M. S., Pandey, B. N., Singh, A., Mishra, A. K., & Pandey, B. K. (2025) · Wiley eBooks · doi:10.1002/9781394287062.ch5 · Cited by 2
Qian, Q., Cheng, M., Zhou, Y., Ding, Y., & Qi, Z. (2021) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom53373.2021.00094 · Cited by 2
Nelli, E. A. S. (2023) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v11i11.9950 · Cited by 2
Foundational Models for Malware Embeddings Using Spatio-Temporal Parallel Convolutional Networks
Nandakumar, D., Quinn, D., Soba, E., Kim, E., Redino, C., Chan, C., Choi, K., Rahman, A., & Bowen, E. (2024) · 2012 International Conference on Computing, Networking and Communications (ICNC) · doi:10.1109/icnc59896.2024.10556354 · Cited by 2
“Similarly, several works [9] [10] [11] utilized convolutional neural networks to classify malware strains.”
Background
Metadata
- Authors
- Lo, W. W., Yang, X., & Wang, Y.
- Affiliations
- Macao Polytechnic University (MO)
- Venue
- 2019 10th IFIP International Conference on New Technologies, Mobility and Security (NTMS)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 1-5
- OpenAlex
- W2960023330
- Cited by
- 122
- References
- 11
- Citations by year
- 2026: 4 · 2025: 18 · 2024: 22 · 2023: 37 · 2022: 24 · 2021: 14 · 2020: 3
- FWCI
- 7.86
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IFIP International Conference on New Technologies, Mobility and Security (NTMS) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Software › Advanced Malware Detection Techniques
- Physical Sciences › Computer Science › Hardware and Architecture › Security and Verification in Computing
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Keywords
- malware classification, Xception, convolutional neural networks, transfer learning, image-based malware classification, ensemble learning, Malimg dataset
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.