Application of Deep Learning Algorithm for Web Shell Detection in Web Application Security System
Open accessAbstract
A web shell is a script executed on a web server, often used by hackers to gain control over an infected server. Detecting web shells is challenging due to their complex behavior patterns. This research focuses on using a deep learning approach to detect web shells on the ISB Atma Luhur web server, aiming to develop a model capable of precise detection. By training the model with labeled PHP files, malicious web shells are distinguished from benign files. The study is crucial for enhancing the server's security, preventing hacker attacks, and safeguarding sensitive data. Through preprocessing techniques such as opcode extraction and feature selection, useful pattern recognition for web shell detection is achieved. Training deep learning models like CNN and RNN with LSTM on processed data leads to accuracy evaluation using classification metrics. The CNN model demonstrates superior performance in detection, emphasizing the effectiveness of deep learning for web shell detection. The research contributes to enhancing security in web-based applications, protecting against cyber threats like web shells.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Without executable permission, a shell script cannot be launched directly from the terminal.
“Without this, a script cannot be launched directly from the terminal (Yuranda and Negara 2024)”
From Modern Approaches to Unix Automation: Shell Scripting, Configuration Management, and Security (2025) · cites this paper as Yuranda and Negara 2024
The Introduction discusses scripts executed by a web server, not scripts launched directly from a terminal. Searches for executable permission, terminal execution, and chmod found no passage addressing whether that permission is required. (LLM, conf=0.74)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 10
- T. Sutabri, A. Wijaya, M. I. Herdiansyah, og E. S. Negara, "Evaluasi Risiko Celah Keamanan Aplikasi E-Office menggunakan Metode OWASP", EDUMATIC, bd. Vol. 8 No. 1, s. 113-122, jun. 2024, doi: 10.29408/edumatic.v8i1.25463. · DOI
- I. Putra, "Live Forensics untuk mengenali Karakteristik Serangan File Upload Guna Meningkatkan Keamanan pada Web Server: Indonesia", jiip, bd. 6, nr. 6, s. 4387-4394, jun. 2023, doi: 10.54371/jiip.v6i6.2173. · DOI
- G. Tianmin, Z. Jiemin, og M. Jian, "Research on Webshell Detection Method Based on Machine Learning", i 2019 3rd International Conference on Electronic Information Technology and Computer Engineering (EITCE), Xiamen, China: IEEE, okt. 2019, s. 1391-1394. doi: 10.1109/EITCE47263.2019.9094767. · DOI
- C. N. Kamath, S. S. Bukhari, og A. Dengel, "Comparative Study between Traditional Machine Learning and Deep Learning Approaches for Text Classification", i Proceedings of the ACM Symposium on Document Engineering 2018, Halifax NS Canada: ACM, aug. 2018, s. 1-11. doi: 10.1145/3209280.3209526. · DOI
- M. Zulqarnain, R. Ghazali, Y. M. M. Hassim, og M. Rehan, "A comparative review on deep learning models for text classification", IJEECS, bd. 19, nr. 1, s. 325, jul. 2020, doi: 10.11591/ijeecs.v19.i1.pp325-335. · DOI
- P. Semberecki og H. Maciejewski, "Deep Learning methods for Subject Text Classification of Articles", præsenteret ved 2017 Federated Conference on Computer Science and Information Systems, Annals of Computer Science and Information Systems, sep. 2017, s. 357-360. doi: 10.15439/2017F414. · DOI
- I. P. Putri, T. Terttiaavini, og N. Arminarahmah, "Analisis Perbandingan Algoritma Machine Learning untuk Prediksi Stunting pada Anak: Comparative Analysis of Machine Learning Algorithms for Predicting Child Stunting", MALCOM, bd. 4, nr. 1, s. 257-265, jan. 2024, doi: 10.57152/malcom.v4i1.1078. · DOI
- N.-H. Nguyen, V.-H. Le, V.-O. Phung, og P.-H. Du, "Toward a Deep Learning Approach for Detecting PHP Webshell", i Proceedings of the Tenth International Symposium on Information and Communication Technology -SoICT 2019, Hanoi, Ha Long Bay, Viet Nam: ACM Press, 2019, s. 514-521. doi: 10.1145/3368926.3369733. · DOI
- L. T. Flannelly, K. J. Flannelly, og K. R. B. Jankowski, "Independent, Dependent, and Other Variables in Healthcare and Chaplaincy Research", Journal of Health Care Chaplaincy, bd. 20, nr. 4, s. 161-170, okt. 2014, doi: 10.1080/08854726.2014.959374. · DOI
- T. Mikolov, K. Chen, G. Corrado, og J. Dean, "Efficient Estimation of Word Representations in Vector Space", 6. september 2013, arXiv: arXiv:1301.3781. Set: 25. juli 2024. [Online]. Tilgængelig hos: http://arxiv.org/abs/1301.3781 · arXiv
Cited by
Sorted by citations
Modern Approaches to Unix Automation: Shell Scripting, Configuration Management, and Security
Madamanchi, S. R. (2025) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2025.72773 · Cited by 2 · see citing works
- Authors
- Yuranda, R., & Negara, E. S.
- Affiliations
- Universitas Bina Darma (ID)
- ORCID
- Negara, Edi Surya
- Venue
- Jurnal Sisfokom (Sistem Informasi dan Komputer)
- Published
- 2024-11-20
- Volume
- 13
- Issue
- 3
- Pages
- 330-336
- ISSN
- 2301-7988 (ISSN-L)
- 2581-0588
- OpenAlex
- W4404664938
- Cited by
- 1
- References
- 0
- Citations by year
- 2025: 1
- FWCI
- 0.38
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Locations
- Jurnal Sisfokom (Sistem Informasi dan Komputer) (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Information Systems › Web Application Security Vulnerabilities
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- web application security, feature selection, convolutional neural networks, LSTM, malware classification, server security
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
