Output details
11 - Computer Science and Informatics
Edinburgh Napier University
Return to search
Output 0 of 0 in the submission
Article title
Approaches to the classification of high entropy file fragments
Type
D - Journal article
Title of journal
Digital Investigation
Article number
-
Volume number
n/a
Issue number
-
First page of article
1
ISSN of journal
17422876
Year of publication
2013
URL
-
Number of additional authors
2
Additional information
<29>The rigor of this paper is identified with the range of experiments on real-life data sets, which range from a 512 byte segment size to 16KB, along with comparing neural network training methods. It is one of the first papers which has applied methods of identify the difference between encrypted and compressed files, using fragments which are not at the start or end of the files, with well defined test data (GovDoc) which supports repeatable experiments. The success rate of 91% for encrypted fragments and 82% for compressed fragments are better than any other research team have achieved.
Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
-
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-