Code Characterization With Graph Convolutions and Capsule Networks
We propose SiCaGCN, a learning system to predict the similarity of a given software code to a set of codes that are permitted to run on a computational resource, such as a supercomputer or a cloud server. This code characterization allows us to detect abusive codes. Our system relies on a structural...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9149622/ |
| _version_ | 1818433202437488640 |
|---|---|
| author | Poornima Haridas Gopinath Chennupati Nandakishore Santhi Phillip Romero Stephan Eidenbenz |
| author_facet | Poornima Haridas Gopinath Chennupati Nandakishore Santhi Phillip Romero Stephan Eidenbenz |
| author_sort | Poornima Haridas |
| collection | DOAJ |
| description | We propose SiCaGCN, a learning system to predict the similarity of a given software code to a set of codes that are permitted to run on a computational resource, such as a supercomputer or a cloud server. This code characterization allows us to detect abusive codes. Our system relies on a structural analysis of the control-flow graph of the software codes and two different graph similarity measures: Graph Edit Distance (GED) and a singular values based metric. SiCaGCN combines elements of Graph Convolutional Neural Networks (GCN), Capsule networks, attention mechanism, and neural tensor networks. Our experimental results include a study of the trade-offs between the two similarity metrics and two variations of our learning networks, with and without the use of capsules. Our main findings are that the use of capsules reduces mean square error significantly for both similarity metrics. Use of capsules reduces the runtime to calculate the GED while increases the runtime of singular values calculation. |
| first_indexed | 2024-12-14T16:17:21Z |
| format | Article |
| id | doaj.art-33f24a14bec14ded914eaf56b38a2538 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T16:17:21Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-33f24a14bec14ded914eaf56b38a25382022-12-21T22:54:53ZengIEEEIEEE Access2169-35362020-01-01813630713631510.1109/ACCESS.2020.30119099149622Code Characterization With Graph Convolutions and Capsule NetworksPoornima Haridas0https://orcid.org/0000-0003-2320-3364Gopinath Chennupati1https://orcid.org/0000-0002-6223-8570Nandakishore Santhi2Phillip Romero3Stephan Eidenbenz4Courant Institute of Mathematical Sciences, New York University, New York City, NY, USALos Alamos National Laboratory, Los Alamos, NM, USALos Alamos National Laboratory, Los Alamos, NM, USALos Alamos National Laboratory, Los Alamos, NM, USALos Alamos National Laboratory, Los Alamos, NM, USAWe propose SiCaGCN, a learning system to predict the similarity of a given software code to a set of codes that are permitted to run on a computational resource, such as a supercomputer or a cloud server. This code characterization allows us to detect abusive codes. Our system relies on a structural analysis of the control-flow graph of the software codes and two different graph similarity measures: Graph Edit Distance (GED) and a singular values based metric. SiCaGCN combines elements of Graph Convolutional Neural Networks (GCN), Capsule networks, attention mechanism, and neural tensor networks. Our experimental results include a study of the trade-offs between the two similarity metrics and two variations of our learning networks, with and without the use of capsules. Our main findings are that the use of capsules reduces mean square error significantly for both similarity metrics. Use of capsules reduces the runtime to calculate the GED while increases the runtime of singular values calculation.https://ieeexplore.ieee.org/document/9149622/Capsule networkscontrol flow graphGCNsimilarityEigen values |
| spellingShingle | Poornima Haridas Gopinath Chennupati Nandakishore Santhi Phillip Romero Stephan Eidenbenz Code Characterization With Graph Convolutions and Capsule Networks IEEE Access Capsule networks control flow graph GCN similarity Eigen values |
| title | Code Characterization With Graph Convolutions and Capsule Networks |
| title_full | Code Characterization With Graph Convolutions and Capsule Networks |
| title_fullStr | Code Characterization With Graph Convolutions and Capsule Networks |
| title_full_unstemmed | Code Characterization With Graph Convolutions and Capsule Networks |
| title_short | Code Characterization With Graph Convolutions and Capsule Networks |
| title_sort | code characterization with graph convolutions and capsule networks |
| topic | Capsule networks control flow graph GCN similarity Eigen values |
| url | https://ieeexplore.ieee.org/document/9149622/ |
| work_keys_str_mv | AT poornimaharidas codecharacterizationwithgraphconvolutionsandcapsulenetworks AT gopinathchennupati codecharacterizationwithgraphconvolutionsandcapsulenetworks AT nandakishoresanthi codecharacterizationwithgraphconvolutionsandcapsulenetworks AT phillipromero codecharacterizationwithgraphconvolutionsandcapsulenetworks AT stephaneidenbenz codecharacterizationwithgraphconvolutionsandcapsulenetworks |