R. G. Gayathri
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
R. G. Gayathri has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Atul Sajjanhar
School of Information Technology, Deakin University, Geelong, VIC 3220, Australia
4 shared publications - Yong Xiang
School of Information Technology, Deakin University, Melbourne, VIC, Australia
4 shared publications Jyothisha J. Nair
Department of Computer Science and Engineering, Amrita Vishwa Vidyapeetham, Amritapuri, Tamil Nadu, India
3 shared publicationsAdithya K Moorthy
Amrita Vishwa Vidyapeetham, Department of Computer Science and Engineering, Amritapuri, India
1 shared publicationAthul Krishna
Amrita Vishwa Vidyapeetham, Department of Computer Science and Engineering, Amritapuri, India
1 shared publicationJyothisha J Nair
Department of Computer Science and Engineering Amrita School of Engineering, Amritapuri, Amrita Vishwa Vidyapeetham, Amrita University, India
1 shared publication
Latest Publications
- Open Access
- 6 May 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (5) , 209
Adversarial Training for Mitigating Insider-Driven XAI-Based Backdoor Attacks
The study investigates how adversarial training techniques can be used to introduce backdoors into deep learning models by an insider with privileged access to training data. The research demonstrates an insider-driven poison-label backdoor approach in which triggers are introduced into the training dataset. These triggers misclassify poisoned inputs while maintaining standard classification on clean data. An adversary can improve the stealth and effectiveness of such attacks by utilizing XAI techniques, which makes the detection of such attacks more difficult. The study uses publicly available datasets to evaluate the robustness of the deep learning models in this situation. Our experiments show that adversarial training considerably reduces backdoor attacks. These results are verified using various performance metrics, revealing model vulnerabilities and possible countermeasures. The findings demonstrate the importance of robust training techniques and effective adversarial defenses to improve the security of deep learning models against insider-driven backdoor attacks.
- 6 May 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (5) , 209
Open AccessAdversarial Training for Mitigating Insider-Driven XAI-Based Backdoor Attacks
The study investigates how adversarial training techniques can be used to introduce backdoors into deep learning models by an insider with privileged access to training data. The research demonstrates an insider-driven poison-label backdoor approach in which triggers are introduced into the training dataset. These triggers misclassify poisoned inputs while maintaining standard classification on clean data. An adversary can improve the stealth and effectiveness of such attacks by utilizing XAI techniques, which makes the detection of such attacks more difficult. The study uses publicly available datasets to evaluate the robustness of the deep learning models in this situation. Our experiments show that adversarial training considerably reduces backdoor attacks. These results are verified using various performance metrics, revealing model vulnerabilities and possible countermeasures. The findings demonstrate the importance of robust training techniques and effective adversarial defenses to improve the security of deep learning models against insider-driven backdoor attacks.
- 19 February 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 249
Hybrid deep learning model using SPCAGAN augmentation for insider threat analysis
- 19 February 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 249
Hybrid deep learning model using SPCAGAN augmentation for insider threat analysis
- Open Access
- 18 July 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (14) , 4945
Image-Based Feature Representation for Insider Threat Classification
Cybersecurity attacks can arise from internal and external sources. The attacks perpetrated by internal sources are also referred to as insider threats. These are a cause of serious concern to organizations because of the significant damage that can be inflicted by malicious insiders. In this paper, we propose an approach for insider threat classification which is motivated by the effectiveness of pre-trained deep convolutional neural networks (DCNNs) for image classification. In the proposed approach, we extract features from usage patterns of insiders and represent these features as images. Hence, images are used to represent the resource access patterns of the employees within an organization. After construction of images, we use pre-trained DCNNs for anomaly detection, with the aim to identify malicious insiders. Random under sampling is used for reducing the class imbalance issue. The proposed approach is evaluated using the MobileNetV2, VGG19, and ResNet50 pre-trained models, and a benchmark dataset. Experimental results show that the proposed method is effective and outperforms other state-of-the-art methods.
- 18 July 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (14) , 4945
Open AccessImage-Based Feature Representation for Insider Threat Classification
Cybersecurity attacks can arise from internal and external sources. The attacks perpetrated by internal sources are also referred to as insider threats. These are a cause of serious concern to organizations because of the significant damage that can be inflicted by malicious insiders. In this paper, we propose an approach for insider threat classification which is motivated by the effectiveness of pre-trained deep convolutional neural networks (DCNNs) for image classification. In the proposed approach, we extract features from usage patterns of insiders and represent these features as images. Hence, images are used to represent the resource access patterns of the employees within an organization. After construction of images, we use pre-trained DCNNs for anomaly detection, with the aim to identify malicious insiders. Random under sampling is used for reducing the class imbalance issue. The proposed approach is evaluated using the MobileNetV2, VGG19, and ResNet50 pre-trained models, and a benchmark dataset. Experimental results show that the proposed method is effective and outperforms other state-of-the-art methods.
- Open Access
Image-Based Feature Representation for Insider Threat Classification
Insiders are the trusted entities in the organization, but poses threat to the with access to sensitive information network and resources. The insider threat detection is a well studied problem in security analytics. Identifying the features from data sources and using them with the right data analytics algorithms makes various kinds of threat analysis possible. The insider threat analysis is mainly done using the frequency based attributes extracted from the raw data available from data sources. In this paper, we propose an image-based feature representation of the daily resource usage pattern of users in the organization. The features extracted from the audit files of the organization are represented as gray scale images. Hence, these images are used to represent the resource access patterns and thereby the behavior of users. Classification models are applied to the representative images to detect anomalous behavior of insiders. The images are classified to malicious and non-malicious. The effectiveness of the proposed representation is evaluated using the CMU CERT data V4.2, and state-of-art image classification models like Mobilenet, VGG and ResNet. The experimental results showed improved accuracy. The comparison with existing works show a performance improvement in terms of high recall and precision values.
Open AccessImage-Based Feature Representation for Insider Threat Classification
Insiders are the trusted entities in the organization, but poses threat to the with access to sensitive information network and resources. The insider threat detection is a well studied problem in security analytics. Identifying the features from data sources and using them with the right data analytics algorithms makes various kinds of threat analysis possible. The insider threat analysis is mainly done using the frequency based attributes extracted from the raw data available from data sources. In this paper, we propose an image-based feature representation of the daily resource usage pattern of users in the organization. The features extracted from the audit files of the organization are represented as gray scale images. Hence, these images are used to represent the resource access patterns and thereby the behavior of users. Classification models are applied to the representative images to detect anomalous behavior of insiders. The images are classified to malicious and non-malicious. The effectiveness of the proposed representation is evaluated using the CMU CERT data V4.2, and state-of-art image classification models like Mobilenet, VGG and ResNet. The experimental results showed improved accuracy. The comparison with existing works show a performance improvement in terms of high recall and precision values.
- 16 May 2019
- Published by Springer Nature
- p. 218-232
Prefix Tree Based MapReduce Approach for Mining Frequent Subgraphs
- 16 May 2019
- Published by Springer Nature
- p. 218-232
Prefix Tree Based MapReduce Approach for Mining Frequent Subgraphs
- 1 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Heuristic Based Ex-FTCD Algorithm for Incremental Path Finding in Dynamic Graphs
The data when modeled as a graph can bring out a lot of useful information. Path finding is one of the most popular applications of network analysis. As the data evolution speed from various sources has grown tremendously, the need for incremental mining is on high demand. Algorithms that compute the shortest path on dynamically changing data needs to be designed. In this paper, we propose a fully dynamic scalable and parallelizable method for finding the all pair shortest path. The work includes computation of the dynamic shortest on network modifications like edge insertion, edge deletion and weight updation, and eliminates recomputing from the scratch. The concept of exact heuristics is applied in the results obtained from the actual network. Validity and efficiency of the proposed method is proved using synthetically generated as well as real world networks.
- 1 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Heuristic Based Ex-FTCD Algorithm for Incremental Path Finding in Dynamic Graphs
The data when modeled as a graph can bring out a lot of useful information. Path finding is one of the most popular applications of network analysis. As the data evolution speed from various sources has grown tremendously, the need for incremental mining is on high demand. Algorithms that compute the shortest path on dynamically changing data needs to be designed. In this paper, we propose a fully dynamic scalable and parallelizable method for finding the all pair shortest path. The work includes computation of the dynamic shortest on network modifications like edge insertion, edge deletion and weight updation, and eliminates recomputing from the scratch. The concept of exact heuristics is applied in the results obtained from the actual network. Validity and efficiency of the proposed method is proved using synthetically generated as well as real world networks.
- 22 March 2018
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 34 (3) , 1643-1652
ex-FTCD: A novel mapreduce model for distributed multi source shortest path problem
Computing the all pair shortest paths in a graph is a widely used solution, but a time-consuming process too. The popularly used conventional algorithms rely solely on the computing capability of the CPU, but fail to meet the demand of real-time processing and mostly do not scale well for larger data. In this paper, we propose the ex-FTCD (extending Full Transitive Closure with Dijkstra’s) algorithm for finding the all pair shortest path by merging the features of the greedy technique in Dijkstra’s single source shortest path method and the transitive closure property. Experiments show that the process improves computing speed and is more scalable. We re-designed the algorithm for the parallel execution and implemented it in mapreduce on Hadoop that supports the conventional map/reduce jobs. This work also includes the implementation on Spark that supports the in-memory computational capability which uses Random Access Memory for computations. The experiments show that the numbers of iterations are relatively small for even large networks.
- 22 March 2018
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 34 (3) , 1643-1652
ex-FTCD: A novel mapreduce model for distributed multi source shortest path problem
Computing the all pair shortest paths in a graph is a widely used solution, but a time-consuming process too. The popularly used conventional algorithms rely solely on the computing capability of the CPU, but fail to meet the demand of real-time processing and mostly do not scale well for larger data. In this paper, we propose the ex-FTCD (extending Full Transitive Closure with Dijkstra’s) algorithm for finding the all pair shortest path by merging the features of the greedy technique in Dijkstra’s single source shortest path method and the transitive closure property. Experiments show that the process improves computing speed and is more scalable. We re-designed the algorithm for the parallel execution and implemented it in mapreduce on Hadoop that supports the conventional map/reduce jobs. This work also includes the implementation on Spark that supports the in-memory computational capability which uses Random Access Memory for computations. The experiments show that the numbers of iterations are relatively small for even large networks.
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2000-2004
All pair shortest path using distributed architectures
Due to the explosion of data from various sources, data analytics is found to be difficult using the CPU alone. For huge networks, the most popular graph algorithms using a single processor failed to accomplish this task. Hence the need of algorithms that have higher processing capabilities became dominant. Graph analytics is gaining importance in the realm of data analysis due to the advantages over other conventional analytical methods. All pair shortest path problem or path-finding problem has applications in various fields. Finding the all pair shortest path in a graph is computationally complex and time consuming in the case of large networks. In this paper, we propose a map reduce approach using the in-memory computation for finding the all pair shortest path using the transitive closure property and the greedy technique in Dijkstra's single source shortest path method. In order to overcome the scalability issues in the network representation, we use a tuple based network representation. The performance of the proposed method is proved experimentally.
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2000-2004
All pair shortest path using distributed architectures
Due to the explosion of data from various sources, data analytics is found to be difficult using the CPU alone. For huge networks, the most popular graph algorithms using a single processor failed to accomplish this task. Hence the need of algorithms that have higher processing capabilities became dominant. Graph analytics is gaining importance in the realm of data analysis due to the advantages over other conventional analytical methods. All pair shortest path problem or path-finding problem has applications in various fields. Finding the all pair shortest path in a graph is computationally complex and time consuming in the case of large networks. In this paper, we propose a map reduce approach using the in-memory computation for finding the all pair shortest path using the transitive closure property and the greedy technique in Dijkstra's single source shortest path method. In order to overcome the scalability issues in the network representation, we use a tuple based network representation. The performance of the proposed method is proved experimentally.
- 1 April 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 0663-0668
Mapreduce model for finding closely knit communities in large scale networks
In this paper, we propose a scalable method for finding the evolving communities in complex networks. The various network properties that are prominent in real-world networks are studied. The proposed algorithm computes the edge betweenness based on the transitive closure property combined with the greedy approach applied in Dijkstra's single source shortest path method. The major contribution is an improvement to GN algorithm in linear time for weighted undirected networks. The proposed algorithm is applied on Mapreduce to prove its scalability and enhance the performance in managing and analyzing the large scale networks. The experimentation of the distributed algorithm is tested on the private cluster and the results are as expected in the theoretical analysis.
- 1 April 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 0663-0668
Mapreduce model for finding closely knit communities in large scale networks
In this paper, we propose a scalable method for finding the evolving communities in complex networks. The various network properties that are prominent in real-world networks are studied. The proposed algorithm computes the edge betweenness based on the transitive closure property combined with the greedy approach applied in Dijkstra's single source shortest path method. The major contribution is an improvement to GN algorithm in linear time for weighted undirected networks. The proposed algorithm is applied on Mapreduce to prove its scalability and enhance the performance in managing and analyzing the large scale networks. The experimentation of the distributed algorithm is tested on the private cluster and the results are as expected in the theoretical analysis.
- Open Access
- 1 January 2016
- Published by Elsevier in Procedia Computer Science
- Vol. 93, 995-1002
Extending Full Transitive Closure to Rank Removable Edges in GN Algorithm
- 1 January 2016
- Published by Elsevier in Procedia Computer Science
- Vol. 93, 995-1002
Open AccessExtending Full Transitive Closure to Rank Removable Edges in GN Algorithm