Mohammadreza Binesh Marvasti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Mohammadreza Binesh Marvasti has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Seyyed Amir Asghari
Department of Electrical and Computer Engineering, Kharazmi University, Tehran, Iran
4 shared publications - Amir M. Rahmani
University of California, Irvine, Irvine, California, USA
2 shared publications Ali-Asghar Salehpour
Department of Electrical and Computer Eng., University of Tehran, Iran
1 shared publicationAmir-Mohammad Rahmani
Department of Electrical and Computer Eng., University of Tehran, Iran
1 shared publication- Asal Khanbadr
Department of Electrical and Computer Engineering, Kharazmi University, Tehran, Iran
1 shared publication Behnam Shamshirsaz
Kharazmi Univ, Dept Elect & Comp Engn, Tehran, Iran
1 shared publication
Latest Publications
- Open Access
- 22 December 2025
- Published by Springer Nature in Research Square
GuardianNet: A Lightweight Intrusion Detection System Using Unsupervised Layer-wise Deep Auto-encoder and Bidirectional Long Short-Term Memory for Binary Classification
As digital infrastructure expands, the threat of network intrusions grows, especially from interconnected networks like the Internet of Things and cloud computing. Reliable intrusion detection systems are essential. Deep learning excels at identifying complex patterns but struggles with overfitting and gradient vanishing, limiting effectiveness. To address these challenges, a recent study proposes a framework called GuardianNet, combining an unsupervised layer-wise deep autoencoder with a bidirectional long short-term memory network optimized through hyperparameter tuning processes. This approach improves the ability of the intrusion detection system to extract vital features from raw data, thereby enhancing its ability to distinguish attacks from benign connections. The effectiveness of the proposed approach was evaluated on three benchmark datasets called KDDCUP99, UNSW-NB15, and CICIDS17. Two experiments were conducted on these datasets to justify the methods adopted in GuardianNet. Finally, a comparison is employed between several state-of-the-art methodologies and ours regarding frequent evaluation criteria in the domain.
- 22 December 2025
- Published by Springer Nature in Research Square
Open AccessGuardianNet: A Lightweight Intrusion Detection System Using Unsupervised Layer-wise Deep Auto-encoder and Bidirectional Long Short-Term Memory for Binary Classification
As digital infrastructure expands, the threat of network intrusions grows, especially from interconnected networks like the Internet of Things and cloud computing. Reliable intrusion detection systems are essential. Deep learning excels at identifying complex patterns but struggles with overfitting and gradient vanishing, limiting effectiveness. To address these challenges, a recent study proposes a framework called GuardianNet, combining an unsupervised layer-wise deep autoencoder with a bidirectional long short-term memory network optimized through hyperparameter tuning processes. This approach improves the ability of the intrusion detection system to extract vital features from raw data, thereby enhancing its ability to distinguish attacks from benign connections. The effectiveness of the proposed approach was evaluated on three benchmark datasets called KDDCUP99, UNSW-NB15, and CICIDS17. Two experiments were conducted on these datasets to justify the methods adopted in GuardianNet. Finally, a comparison is employed between several state-of-the-art methodologies and ours regarding frequent evaluation criteria in the domain.
- 18 January 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (2) , 1-23
Improve accuracy in CNNs while using approximate computing methods
- 18 January 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (2) , 1-23
Improve accuracy in CNNs while using approximate computing methods
- 1 January 2022
- Published by Zarqa University in The International Arab Journal of Information Technology
- Vol. 19 (4) , 652-659
An Improved Process Supervision and Control Method for Malware Detection
- 1 January 2022
- Published by Zarqa University in The International Arab Journal of Information Technology
- Vol. 19 (4) , 652-659
An Improved Process Supervision and Control Method for Malware Detection
- 16 March 2020
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 76 (12) , 10186-10211
A novel method for victim block selection for NAND flash-based solid state drives based on scoring
- 16 March 2020
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 76 (12) , 10186-10211
A novel method for victim block selection for NAND flash-based solid state drives based on scoring
- 4 February 2020
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 76 (11) , 8901-8921
CA-Dedupe: content-aware deduplication in SSDs
- 4 February 2020
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 76 (11) , 8901-8921
CA-Dedupe: content-aware deduplication in SSDs
- 7 May 2019
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 78, 520-535
FRCD: Fast recovery of compressible data in flash memories
- 7 May 2019
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 78, 520-535
FRCD: Fast recovery of compressible data in flash memories
- 1 August 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 526-529
A novel test environment for template based QDI asynchronous circuits
In this paper, we propose an efficient test environment for template based asynchronous circuits. This test environment consists of two major parts: fault simulation and test pattern generation. The fault simulation is based on exploring fault effect on quasi-delay insensitive asynchronous circuits that detects any changes in sequences of predefined signals. The test pattern generation is a high level method based on signal transition graph. The effectiveness of the proposed test environment is shown by experimental results on a set of benchmarks given in the form of templates.
- 1 August 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 526-529
A novel test environment for template based QDI asynchronous circuits
In this paper, we propose an efficient test environment for template based asynchronous circuits. This test environment consists of two major parts: fault simulation and test pattern generation. The fault simulation is based on exploring fault effect on quasi-delay insensitive asynchronous circuits that detects any changes in sequences of predefined signals. The test pattern generation is a high level method based on signal transition graph. The effectiveness of the proposed test environment is shown by experimental results on a set of benchmarks given in the form of templates.