Mahmoud Zamani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mahmoud Zamani has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Latifur Khan
The University of Texas at Dallas
9 shared publications - Kevin W. Hamlen
The University of Texas at Dallas
7 shared publications - Xiaodi Li
The University of Texas at Dallas
4 shared publications - Saquib Irtiza
The University of Texas at Dallas
3 shared publications - Shamila Wickramasuriya
The University of Texas at Dallas
3 shared publications - Bhavani Thuraisingham
The University of Texas at Dallas, Richardson, Texas, USA
2 shared publications
Latest Publications
- Open Access
PPSEBM: An Energy-Based Model with Progressive Parameter Selection for Continual Learning
Continual learning remains a fundamental challenge in machine learning, requiring models to learn from a stream of tasks without forgetting previously acquired knowledge. A major obstacle in this setting is catastrophic forgetting, where performance on earlier tasks degrades as new tasks are learned. In this paper, we introduce PPSEBM, a novel framework that integrates an Energy-Based Model (EBM) with Progressive Parameter Selection (PPS) to effectively address catastrophic forgetting in continual learning for natural language processing tasks. In PPSEBM, progressive parameter selection allocates distinct, task-specific parameters for each new task, while the EBM generates representative pseudo-samples from prior tasks. These generated samples actively inform and guide the parameter selection process, enhancing the model's ability to retain past knowledge while adapting to new tasks. Experimental results on diverse NLP benchmarks demonstrate that PPSEBM outperforms state-of-the-art continual learning methods, offering a promising and robust solution to mitigate catastrophic forgetting.
Open AccessPPSEBM: An Energy-Based Model with Progressive Parameter Selection for Continual Learning
Continual learning remains a fundamental challenge in machine learning, requiring models to learn from a stream of tasks without forgetting previously acquired knowledge. A major obstacle in this setting is catastrophic forgetting, where performance on earlier tasks degrades as new tasks are learned. In this paper, we introduce PPSEBM, a novel framework that integrates an Energy-Based Model (EBM) with Progressive Parameter Selection (PPS) to effectively address catastrophic forgetting in continual learning for natural language processing tasks. In PPSEBM, progressive parameter selection allocates distinct, task-specific parameters for each new task, while the EBM generates representative pseudo-samples from prior tasks. These generated samples actively inform and guide the parameter selection process, enhancing the model's ability to retain past knowledge while adapting to new tasks. Experimental results on diverse NLP benchmarks demonstrate that PPSEBM outperforms state-of-the-art continual learning methods, offering a promising and robust solution to mitigate catastrophic forgetting.
- 10 July 2025
- Published by Springer Nature
- p. 96-117
CodeGrafter: Unifying Source and Binary Graphs for Robust Vulnerability Detection
- 10 July 2025
- Published by Springer Nature
- p. 96-117
CodeGrafter: Unifying Source and Binary Graphs for Robust Vulnerability Detection
- Open Access
LSEBMCL: A Latent Space Energy-Based Model for Continual Learning
Continual learning has become essential in many practical applications such as online news summaries and product classification. The primary challenge is known as catastrophic forgetting, a phenomenon where a model inadvertently discards previously learned knowledge when it is trained on new tasks. Existing solutions involve storing exemplars from previous classes, regularizing parameters during the fine-tuning process, or assigning different model parameters to each task. The proposed solution LSEBMCL (Latent Space Energy-Based Model for Continual Learning) in this work is to use energy-based models (EBMs) to prevent catastrophic forgetting by sampling data points from previous tasks when training on new ones. The EBM is a machine learning model that associates an energy value with each input data point. The proposed method uses an EBM layer as an outer-generator in the continual learning framework for NLP tasks. The study demonstrates the efficacy of EBM in NLP tasks, achieving state-of-the-art results in all experiments.
Open AccessLSEBMCL: A Latent Space Energy-Based Model for Continual Learning
Continual learning has become essential in many practical applications such as online news summaries and product classification. The primary challenge is known as catastrophic forgetting, a phenomenon where a model inadvertently discards previously learned knowledge when it is trained on new tasks. Existing solutions involve storing exemplars from previous classes, regularizing parameters during the fine-tuning process, or assigning different model parameters to each task. The proposed solution LSEBMCL (Latent Space Energy-Based Model for Continual Learning) in this work is to use energy-based models (EBMs) to prevent catastrophic forgetting by sampling data points from previous tasks when training on new ones. The EBM is a machine learning model that associates an energy value with each input data point. The proposed method uses an EBM layer as an outer-generator in the continual learning framework for NLP tasks. The study demonstrates the efficacy of EBM in NLP tasks, achieving state-of-the-art results in all experiments.
- 13 July 2024
- Published by Springer Nature
- p. 71-91
Ensuring End-to-End IoT Data Security and Privacy Through Cloud-Enhanced Confidential Computing
- 13 July 2024
- Published by Springer Nature
- p. 71-91
Ensuring End-to-End IoT Data Security and Privacy Through Cloud-Enhanced Confidential Computing
- 13 July 2024
- Published by Springer Nature
- p. 221-240
VulPrompt: Prompt-Based Vulnerability Detection Using Few-Shot Graph Learning
- 13 July 2024
- Published by Springer Nature
- p. 221-240
VulPrompt: Prompt-Based Vulnerability Detection Using Few-Shot Graph Learning
- 25 April 2024
- Published by Springer Nature
- p. 191-207
VulMAE: Graph Masked Autoencoders for Vulnerability Detection from Source and Binary Codes
- 25 April 2024
- Published by Springer Nature
- p. 191-207
VulMAE: Graph Masked Autoencoders for Vulnerability Detection from Source and Binary Codes
- 10 November 2023
- Published by SAGE Publications in Journal of Computer Security
- Vol. 31 (6) , 705-726
Con2Mix: A semi-supervised method for imbalanced tabular security data1
Con2Mix (Contrastive Double Mixup) is a new semi-supervised learning methodology that innovates a triplet mixup data augmentation approach for finding code vulnerabilities in imbalanced, tabular security data sets. Tabular data sets in cybersecurity domains are widely known to pose challenges for machine learning because of their heavily imbalanced data (e.g., a small number of labeled attack samples buried in a sea of mostly benign, unlabeled data). Semi-supervised learning leverages a small subset of labeled data and a large subset of unlabeled data to train a learning model. While semi-supervised methods have been well studied in image and language domains, in security domains they remain underutilized, especially on tabular security data sets which pose especially difficult contextual information loss and balance challenges for machine learning. Experiments applying Con2Mix to collected security data sets show promise for addressing these challenges, achieving state-of-the-art performance on two evaluated data sets compared with other methods.
- 10 November 2023
- Published by SAGE Publications in Journal of Computer Security
- Vol. 31 (6) , 705-726
Con2Mix: A semi-supervised method for imbalanced tabular security data1
Con2Mix (Contrastive Double Mixup) is a new semi-supervised learning methodology that innovates a triplet mixup data augmentation approach for finding code vulnerabilities in imbalanced, tabular security data sets. Tabular data sets in cybersecurity domains are widely known to pose challenges for machine learning because of their heavily imbalanced data (e.g., a small number of labeled attack samples buried in a sea of mostly benign, unlabeled data). Semi-supervised learning leverages a small subset of labeled data and a large subset of unlabeled data to train a learning model. While semi-supervised methods have been well studied in image and language domains, in security domains they remain underutilized, especially on tabular security data sets which pose especially difficult contextual information loss and balance challenges for machine learning. Experiments applying Con2Mix to collected security data sets show promise for addressing these challenges, achieving state-of-the-art performance on two evaluated data sets compared with other methods.
- Open Access
- 24 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 153-164
Confidential Execution of Deep Learning Inference at the Untrusted Edge with ARM TrustZone
This paper proposes a new confidential deep learning (DL) inference system with ARM TrustZone to provide confidentiality and integrity of DL models and data in an untrusted edge device with limited memory. Although ARM TrustZone supplies a strong, hardware-supported trusted execution environment for protecting sensitive code and data in an edge device against adversaries, resource limitations in typical edge devices have raised significant challenges for protecting on-device DL requiring large memory consumption without sacrificing the security and accuracy of the model. The proposed solution addresses this challenge without modifying the protected DL model, thereby preserving the original prediction accuracy. Comprehensive experiments using different DL architectures and datasets demonstrate that inference services for large and complex DL models can be deployed in edge devices with TrustZone with limited trusted memory, ensuring data confidentiality and preserving the original model's prediction exactness.
- 24 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 153-164
Open AccessConfidential Execution of Deep Learning Inference at the Untrusted Edge with ARM TrustZone
This paper proposes a new confidential deep learning (DL) inference system with ARM TrustZone to provide confidentiality and integrity of DL models and data in an untrusted edge device with limited memory. Although ARM TrustZone supplies a strong, hardware-supported trusted execution environment for protecting sensitive code and data in an edge device against adversaries, resource limitations in typical edge devices have raised significant challenges for protecting on-device DL requiring large memory consumption without sacrificing the security and accuracy of the model. The proposed solution addresses this challenge without modifying the protected DL model, thereby preserving the original prediction accuracy. Comprehensive experiments using different DL architectures and datasets demonstrate that inference services for large and complex DL models can be deployed in edge devices with TrustZone with limited trusted memory, ensuring data confidentiality and preserving the original model's prediction exactness.
- 13 July 2022
- Published by Springer Nature
- p. 48-67
MCoM: A Semi-Supervised Method for Imbalanced Tabular Security Data
- 13 July 2022
- Published by Springer Nature
- p. 48-67
MCoM: A Semi-Supervised Method for Imbalanced Tabular Security Data