Scribd
Upload
7 views

Software Needs

This document reviews 5 papers on file type identification and characterization published between 2011-2017. It summarizes the title/problem, methodology, results, and proposed future work of each paper. The papers propose and evaluate various machine learning and statistical techniques like neural networks, genetic algorithms, principle component analysis to identify file types from intact files as well as fragmented files, with accuracy ranging from 98-100% in most cases. Future work suggested includes exploring other algorithms to improve accuracy and efficiency of file type detection.

Uploaded by

Sara Ghulam Muhammad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
7 views

Software Needs

This document reviews 5 papers on file type identification and characterization published between 2011-2017. It summarizes the title/problem, methodology, results, and proposed future work of each paper. The papers propose and evaluate various machine learning and statistical techniques like neural networks, genetic algorithms, principle component analysis to identify file types from intact files as well as fragmented files, with accuracy ranging from 98-100% in most cases. Future work suggested includes exploring other algorithms to improve accuracy and efficiency of file type detection.

Uploaded by

Sara Ghulam Muhammad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Sara Ghulam Muhammad

A Review on Papers
Title/Problem Year Methodology Result Future Work

Recognition of File 2017 A three-stage process The accuracy of the If for results is
Type after change involving feature extraction proposed method to neural network
(BFD), feature selection altered jpg images and used rather
(genetic algorithm), and to gif images was then k-means
classification (neural 100%, to altered png clustering
network) was proposed. images was 98,81% algorithm
and to altered tiff improve result.
images was 98,21%.
File Formats - 2016 This paper uses the strategy It shows 98.7% result.
Characterization to merge the outputs of
and Validation three tools JHOVE,
DROID, and Exiftools
from tests conducted
towards the same dataset.
Feature-based Type 2013 A content-based method Its accuracy and speed Accuracy and
Identification of that deploys principle is also significant for speed can be
File Fragments component analysis and the case of file enhanced
neural networks for an fragments, where data using different
automatic feature is captured from algorithms.
extraction is proposed. The random starting points
extracted features are then within files, but the
applied to a classifier for accuracy differs
the type detection according to the
lengths of file
fragments.
File fragment 2013 A new tool, zsniff, which The results offer a
encoding allows analyzing deflate- conceptually new type
classification—An encoded data, and it used to of classification
empirical approach perform an empirical capabilities that
survey of deflate-coded cannot be achieved by
text, images, and other means.
executable.
The application of 2011 Digital tool is developed to It is possible to
file identification, perform file format generate files
validation, and identification, with nothing
characterization characterization, and more than a
tools in digital validation actions. proper file
curation extension and
correct magic
number and
have the tools
"positively"
identify the
file.
References:

1. Karampidis, K., & Papadourakis, G. (2017). File Type Identification-


Computational Intelligence for Digital Forensics. Journal of Digital Forensics,
Security and Law, 12(2), 6.
2. Roussev, V., & Quates, C. (2013). File fragment encoding classification—An
empirical approach. Digital Investigation, 10, S69-S77.
3. Ford, K. M. (2011). The application of file identification, validation, and
characterization tools in digital curation.
4. Shala, L., & Shala, A. (2016). File Formats-Characterization and Validation.
IFAC-PapersOnLine, 49(29), 253-258.
5. Amirani, M. C., Toorani, M., & Mihandoost, S. (2013). Feature‐based Type
Identification of File Fragments. Security and Communication Networks, 6(1),
115-128.

You might also like