A novel context-aware feature extraction method for convolutional neural network-based intrusion detection systems

Shams, Erfan A.; Rızaner, Ahmet; Ulusoy, Ali Hakan

doi:10.1007/s00521-021-05994-9

Cited by 43 publications

(7 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research on the IMDB movie dataset has brought substantial advancements across diverse domains. Notably, breakthroughs have been made in network security through Intrusion Detection Systems (IDSs) that identify intrusions and enhance accuracy using context-aware feature extraction [1]. Concurrently, predictive models for film success, employing RoBERTa embeddings and neural networks, seek to optimize decisions and investments within the film industry [2].…”

Section: Related Workmentioning

confidence: 99%

Deep learning for sentiment analysis on IMDB movie reviews using N-gram features

Ouyang

2024

ACE

View full text Add to dashboard Cite

In the rapidly evolving digital landscape, the synergy of deep learning techniques and abundant datasets has opened new frontiers in various domains. This research delves into the film industry, specifically harnessing the potential of the International Movie DataBase (IMDB) dataset for sentiment analysis. Through a deep learning paradigm, we embark on sentiment classification of movie reviews, discerning between positive and negative sentiments. By navigating data preprocessing and N-gram feature extraction, we engineer a deep learning model comprising embedding, global average pooling, and multi-layer dense architectures. The experimental results underscore the model's prowess in sentiment analysis, emphasizing its capacity to empower informed decision-making within the film industry.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep learning for sentiment analysis on IMDB movie reviews using N-gram features

Ouyang

2024

ACE

View full text Add to dashboard Cite

show abstract

“…The parallel genetic algorithm was implemented with an open-source MapReduce library that helps select better features. The authors of [21] presented a network intrusion detection mechanism where a CNN model based on contextual feature extraction improves the accuracy of the IDS. The approach reduced the feature set before feeding it into a CNN to reduce the computational time.…”

Section: Related Workmentioning

confidence: 99%

Efficient Intrusion Detection System in the Cloud Using Fusion Feature Selection Approaches and an Ensemble Classifier

et al. 2023

View full text Add to dashboard Cite

The application of cloud computing has increased tremendously in both public and private organizations. However, attacks on cloud computing pose a serious threat to confidentiality and data integrity. Therefore, there is a need for a proper mechanism for detecting cloud intrusions. In this paper, we have proposed a cloud intrusion detection system (IDS) that is focused on boosting the classification accuracy by improving feature selection and weighing the ensemble model with the crow search algorithm (CSA). The feature selection is handled by combining both filter and automated models to obtain improved feature sets. The ensemble classifier is made up of machine and deep learning models such as long short-term memory (LSTM), support vector machine (SVM), XGBoost, and a fast learning network (FLN). The proposed ensemble model’s weights are generated with the CSA to obtain better prediction results. Experiments are executed on the NSL-KDD, Kyoto, and CSE-CIC-IDS-2018 datasets. The simulation shows that the suggested system attained more satisfactory results in terms of accuracy, recall, precision, and F-measure than conventional approaches. The detection rate and false alarm rate (FAR) of different attack types was more efficient for each dataset. The classifiers’ performances were also compared individually to the ensemble model in terms of the false positive rate (FPR) and false negative rate (FNR) to demonstrate the ensemble model’s robustness.

show abstract

“…In the field of information security, deep learning algorithms are widely applied in IDS, which provides more technical support for the enhancement of IDS performance. Shams E A et al [6] proposed a convolutional neural network model, the feature extraction method is context awareness, which can reduce the feature space and cut down classification time. The classification accuracy was improved by a variety of datasets for performance evaluation and comparison.…”

Section: Related Workmentioning

confidence: 99%

Research on intrusion detection method based on 1D-ICNN-BiGRU

Liu

Niu

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Intrusion detection is one of the effective ways to secure the network. Based the unbalanced network traffic data between different attacks, the intrusion detection algorithm turns out to be low intrusion detection accuracy and low identification rate of minority attacks. To solve the problems, an improved intrusion detection model combined with one-dimensional convolutional neural network and bidirectional gated recurrent unit(1D-ICNN-BiGRU) is proposed. First, the dataset is balanced by the SMOTE-Tomek algorithm, then 1D-ICNN-BiGRU is performed for feature extraction, and the final fully connected layer of the model is replaced by global average pooling. The results show that based on the balanced data, the proposed model achieves higher intrusion detection accuracy for R2L and U2R attack than other classic intrusion detection models. The proposed model also improved the identification rate of minority attacks, making the model accuracy rate reach 95.53%, and the false positive rate is only 2.98%.

show abstract

A novel context-aware feature extraction method for convolutional neural network-based intrusion detection systems

Cited by 43 publications

References 40 publications

Deep learning for sentiment analysis on IMDB movie reviews using N-gram features

Deep learning for sentiment analysis on IMDB movie reviews using N-gram features

Efficient Intrusion Detection System in the Cloud Using Fusion Feature Selection Approaches and an Ensemble Classifier

Research on intrusion detection method based on 1D-ICNN-BiGRU

Contact Info

Product

Resources

About