Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Enhancing anomaly-based zero-day attack detection framework using CNN-driven feature extraction and OC-SVM.

Sudhanshu Sekhar Tripathy1, Bichitrananda Behera2, D Samuel Kollie3

  • 1Department of Computer Science and Engineering, C. V. Raman Global University, Bhubaneswar, Odisha, India.

Scientific Reports
|June 14, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Stacked multi-fusion CNN: an adaptive attention model for privacy preserving deepfake forensics.

Scientific reports·2026
Same author

Cross-Dataset Evaluation of an Automated Video-Based Model for Detecting Tardive Dyskinesia Using the Clinician's Tardive Inventory: Validation Study.

JMIR mental health·2026
Same author

An ensemble-based sentiment analysis approach for precision medicine recommendation.

Scientific reports·2026
Same author

Quantitative Electroencephalographic (qEEG) Characterisation and Biomarker Identification of Generalised Paediatric Seizure Using Spectral Features.

Annals of neurosciences·2026
Same author

Hyperledger Fabric-Powered Digital Identity Scheme: Transforming CIA-Triad Security in IoMT Integrated Healthcare Eco-System.

Blockchain in healthcare today·2026
Same author

Cloud-enabled automatic modulation classification using deep feature fusion and Moth-Flame Optimized ELM approach.

Scientific reports·2025
Same journal

Correction: A method for supervoxel-wise association studies of age and other non-imaging variables from coronary computed tomography angiograms.

Scientific reports·2026
Same journal

Poly(bromophenol blue)/CoSn(OH)<sub>6</sub> cubic particles modified pencil graphite electrode for electrochemical determination of diphenhydramine.

Scientific reports·2026
Same journal

Dietary Chlorella, Spirulina, and acidifier modulate jejunal cytokine-related gene expression in broiler chickens.

Scientific reports·2026
Same journal

Perceived physical activity barriers in university students: associations with fatigue and eating behaviours.

Scientific reports·2026
Same journal

Refuge limitation structures habitat use in agricultural landscapes: evidence from Sunda pangolins.

Scientific reports·2026
Same journal

Lightweight stateless transaction verification with outsourced witness updates for UTXO blockchains.

Scientific reports·2026
See all related articles
This summary is machine-generated.

This study introduces a hybrid semi-supervised CNN+OC-SVM model for detecting zero-day attacks. The framework effectively identifies novel cyber threats by combining deep learning feature extraction with anomaly detection, achieving high accuracy.

Area of Science:

  • Cybersecurity
  • Machine Learning
  • Network Intrusion Detection

Background:

  • Traditional Intrusion Detection Systems (IDS) struggle with zero-day attacks due to their reliance on known signatures.
  • Detecting unknown threats necessitates models that can identify anomalous network traffic patterns without prior knowledge.

Purpose of the Study:

  • To propose and evaluate a hybrid semi-supervised framework for effective zero-day attack detection.
  • To enhance the capability of detecting previously unseen cyber threats.

Main Methods:

  • A hybrid semi-supervised framework integrating Convolutional Neural Network (CNN) for feature extraction and One-Class Support Vector Machine (OC-SVM) for anomaly detection.
  • Implementation of a structured preprocessing pipeline including feature selection, categorical encoding, and normalization.
Keywords:
Anomaly detectionCIC-IDS2017Convolutional neural network (CNN)CybersecurityNSL-KDDNetwork intrusion detection system (NIDS)Semi-supervised learningZero-day attack detection

Related Experiment Videos

  • Evaluation on NSL-KDD and CIC-IDS2017 benchmark datasets, comparing against unsupervised methods like Isolation Forest, K-means, and DBSCAN.

    • Main Results:

    • The CNN+OC-SVM model achieved high accuracy: 98.41% on NSL-KDD and 99.31% on CIC-IDS2017.
    • Precision, recall, and F1-scores exceeded 98%, demonstrating strong classification reliability for both normal and attack classes.
    • The proposed model outperformed baseline unsupervised methods in detecting zero-day attacks.

    Conclusions:

    • The hybrid CNN+OC-SVM framework shows significant effectiveness in detecting zero-day cyber threats.
    • Combining deep feature extraction with anomaly-based learning enhances detection accuracy and robustness against novel attacks.
    • The study validates the potential of advanced machine learning techniques for next-generation cybersecurity solutions.