Adversarial Networks and Machine Learning for File Classification

01/27/2023
by   Ken St. Germain, et al.
0

Correctly identifying the type of file under examination is a critical part of a forensic investigation. The file type alone suggests the embedded content, such as a picture, video, manuscript, spreadsheet, etc. In cases where a system owner might desire to keep their files inaccessible or file type concealed, we propose using an adversarially-trained machine learning neural network to determine a file's true type even if the extension or file header is obfuscated to complicate its discovery. Our semi-supervised generative adversarial network (SGAN) achieved 97.6 We also compared our network against a traditional standalone neural network and three other machine learning algorithms. The adversarially-trained network proved to be the most precise file classifier especially in scenarios with few supervised samples available. Our implementation of a file classifier using an SGAN is implemented on GitHub (https://ksaintg.github.io/SGAN-File-Classier).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/12/2017

A HelloWord Bib stile file .bst

A HelloWord Bib stile file .bst is described...
research
02/17/2010

A new approach to content-based file type detection

File type identification and file type clustering may be difficult tasks...
research
10/29/2020

Short Text Classification Approach to Identify Child Sexual Exploitation Material

Producing or sharing Child Sexual Exploitation Material (CSEM) is a seri...
research
02/25/2021

File fragment recognition based on content and statistical features

Nowadays, the speed up development and use of digital devices such as sm...
research
10/05/2020

Metadata-Based Detection of Child Sexual Abuse Material

In the last decade, the scale of creation and distribution of child sexu...
research
05/01/2023

File Fragment Classification using Light-Weight Convolutional Neural Networks

In digital forensics, file fragment classification is an important step ...
research
07/02/2019

Methodology for the Automated Metadata-Based Classification of Incriminating Digital Forensic Artefacts

The ever increasing volume of data in digital forensic investigation is ...

Please sign up or login with your details

Forgot password? Click here to reset