| Title | Graph Neural Networks for Prevention of Leakage of Secret Data |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Ghouse, Mohammed, Nene, Manisha J. |
| Conference Name | 2020 5th International Conference on Communication and Electronics Systems (ICCES) |
| Date Published | June 2020 |
| Publisher | IEEE |
| ISBN Number | 978-1-7281-5371-1 |
| Keywords | advanced encryption standard (AES), Artificial Intelligence (AI), classification, composability, confinement, Data in Rest (DiT), Data Leakage Prevention (DLP), Graph Neural Networks (GNN), machine learning (ML), privacy, pubcrawl, resilience, Resiliency |
| Abstract | The study presents the design and development of security solution pertaining to prevention of leakage of secret data that is in transit (DIT) to be deployed in a Network Gateway, the Gateway is the link connecting the Trusted Network with the Un-trusted Network. The entire solution includes, tasks such as classification of data flowing in the network, followed by the confinement of the identified data, the confinement of the identified data is done either by tagging the data or by means of encryption, however the later form is employed to achieve confinement of classified data under secret category thereby achieving confidentiality of the same. GNN is used for achieving the categorization function and the results are found to be satisfying with less processing time. The dataset that is used is the publicly available dataset and is available in its labeled format. The final deployment will however be based on the datasets that is available to meet a particular requirement of an Organization/Institution. Any organization can prepare a customized dataset suiting its requirements and train the model. The model can then be used for meeting the DLP requirement. |
| URL | https://ieeexplore.ieee.org/document/9137957 |
| DOI | 10.1109/ICCES48766.2020.9137957 |
| Citation Key | ghouse_graph_2020 |
Graph Neural Networks for Prevention of Leakage of Secret Data