SIFT - File Fragment Classification Without Metadata
| dc.contributor.author | Alam, Shahid | |
| dc.date.accessioned | 2025-01-06T17:29:48Z | |
| dc.date.available | 2025-01-06T17:29:48Z | |
| dc.date.issued | 2023 | |
| dc.description | 3rd International Conference on Computing and Information Technology, ICCIT 2023 -- 13 September 2023 through 14 September 2023 -- Tabuk -- 193403 | |
| dc.description.abstract | A vital issue of file carving in digital forensics is type classification of file fragments when the filesystem metadata is missing. Over the past decades, there have been several efforts for developing methods to classify file fragments. In this research, a novel sifting approach, named SIFT (Sifting File Types), is proposed. SIFT outperforms the other state-of-the-art techniques by at least 8%. (1) One of the significant differences between SIFT and others is that SIFT uses a single byte as a separate feature, i.e., a total of 256 (0×00 - 0×FF) features. We also call this a lossless feature (information) extraction, i.e., there is no loss of information. (2) The other significant difference is the technique used to estimate inter-Classes and intra-Classes information gain of a feature. Unlike others, SIFT adapts TF-IDF for this purpose, and computes and assigns weight to each byte (feature) in a fragment (sample). With these significant differences and approaches, SIFT produces promising (better) results compared to other works. © 2023 IEEE. | |
| dc.identifier.doi | 10.1109/ICCIT58132.2023.10273945 | |
| dc.identifier.endpage | 129 | |
| dc.identifier.isbn | 979-835032148-7 | |
| dc.identifier.scopus | 2-s2.0-85175420636 | |
| dc.identifier.startpage | 123 | |
| dc.identifier.uri | https://doi.org/10.1109/ICCIT58132.2023.10273945 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.14669/1366 | |
| dc.indekslendigikaynak | Scopus | |
| dc.language.iso | en | |
| dc.publisher | Institute of Electrical and Electronics Engineers Inc. | |
| dc.relation.ispartof | 2023 3rd International Conference on Computing and Information Technology, ICCIT 2023 | |
| dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | |
| dc.rights | info:eu-repo/semantics/closedAccess | |
| dc.snmz | KA_20241211 | |
| dc.subject | Classification | |
| dc.subject | Digital forensics | |
| dc.subject | File fragmentation | |
| dc.subject | File types | |
| dc.title | SIFT - File Fragment Classification Without Metadata | |
| dc.type | Conference Object |
