Review on effectiveness of deep learning approach in digital forensics (original) (raw)

Data mining approach for digital forensics task with deep learning techniques

International Journal of Advanced and Applied Sciences, 2020

In the past, digital forensic, with its exploration techniques, are a lane to the data recovery as well as the examination of different investigation techniques. It is a line of investigation which includes many stages. In this, the foremost assignment is data collection later than that the outcome amount produced predicted with the dataset. Some authors proposed several supervised machine learning techniques that have not obtained much better results. Therefore, the goal of our study was to perform an investigational work on a forensics dataset task for class-based classification methods like three-layer CNN classifiers, five-layer CNN classifiers, and seven-layer CNN classifiers. The classifiers evaluated with classification performance and accuracy. The experimental plan has been done with fivefold cross-validation with fifty repetitions for deep learning algorithms in order to obtain consistent results. Matching accuracy values for the next to next pixels in the classes are calculated with the class-based predicted labels. There are four classes assigned on CNN, and the four classes are segmented and separated with the same region of interest. Then the same class-based region of interests is segregated, and these four class-based regions are next given to CNN with the clusters. Further, the comparison results are made with the used three algorithms.

A Review on Application of Deep Learning in Cyber Forensics

International Journal for Research in Applied Science and Engineering Technology IJRASET, 2020

In recent times, most of the data such as books, personal materials and genetic information digitally. This transformation gives rise to a field of Cyberspace. This newly created space, gave rise to a new set of crime Cybercrime, this lead to the development of securing the cyberspace and protecting against cybercrime. As more people started using cyberspace, more number of cybercrime were registered. As the number of crime increases, we are in need of help from Machine Learning. Machine Learning in the field of Cyber forensics, is a boon. In this paper we have an overview of Machine Learning in the field of Cyber Forensics and various method of it implementation. I. INTRODUCTION 1) Deep Learning and Machine Learning: The field of Artificial Intelligence and Machine Learning has been around since a long time but it is now that we have enough computational power to effectively develop strong artificial neural networks (ANN) in a reasonable time frame with the help of strong hardware and software support. The most important aspect of Cyber security involves protecting key data and devices from cyber threats. It's an important part of corporations that collect and maintain large databases of client data, social platforms wherever personal information were submitted and also the government organizations wherever secret, political and defence information comes into measure. Unlike the traditional machine learning algorithm that uses feature engineering and illustration ways. They will chose the best options by themselves. 2) Cyber Security: Cyber security is that the set of framework and processes designed to protect computers, networks, programs, and data from attack, unauthorized access, change, or destruction. These frameworks are consist of network security and host security systems, every of those has a minimum firewall, antivirus computer code, associated an intrusion detection system. 3) Deep Learning and Cyber Security: This survey summarizes the association of cyber security and Deep learning techniques (DL). Deep learning technique are being used by researchers in recent days. Deep learning can be used alongside the prevailing automation ways like rule and heuristics based and machine learning techniques. This survey helps is understand the benefits of deep learning algorithms to classify and tackle malicious activities that perceived from the varied sources like DNS, email, URLs etc. In recent days, non-public firms and public establishments are dealing with constant and complicated cyber threats and cyberattacks. As a precaution, organizations should build and develop a cybersecurity culture and awareness so as to defend against cyber criminals. 4) Shared Task: In this shared task conference, the train data set will be distributed among the participants and the train model will be evaluated based on the test data set. This is most common in NLP area recently shared task on identifying phishing email has been organized by. The details of the submitted runs are available throughout. Followed by shared task on detecting malicious domain organized intruders. These two shared tasks enables the participants to share their approach through working notes or system description paper. Each year there is one more shared task conducted by CDMC. But they don't provide us an option to submit system description papers. But recently they are giving an option to submit system description papers (CDMC 2018). One significant issue was that the available data sets are very old and each data set has their own limitations. The main issue we face now is due to the non-maintenance of Cybercrime data. To overcome such issues a brief investigative issue made to understand the need of Security domain, datasets and key feature of data sciences is discussed in for problems employing the data science towards cyber security. The need for such dataset in to be promoted.

A survey of deepfakes in terms of deep learning and multimedia forensics

International Journal of Electrical and Computer Engineering (IJECE), 2022

Artificial intelligence techniques are reaching us in several forms, some of which are useful but can be exploited in a way that harms us. One of these forms is called deepfakes. Deepfakes is used to completely modify video (or image) content to display something that was not in it originally. The danger of deepfake technology impact on society through the loss of confidence in everything is published. Therefore, in this paper, we focus on deepfake detection technology from the view of two concepts which are deep learning and forensic tools. The purpose of this survey is to give the reader a deeper overview of i) the environment of deepfake creation and detection, ii) how deep learning and forensic tools contributed to the detection of deepfakes, and iii) finally how in the future incorporating both deep learning technology and tools for forensics can increase the efficiency of deepfakes detection.

Non-Facial Video Spatiotemporal Forensic Analysis Using Deep Learning Techniques

Proceedings of Engineering and Technology Innovation

Digital content manipulation software is working as a boon for people to edit recorded video or audio content. To prevent the unethical use of such readily available altering tools, digital multimedia forensics is becoming increasingly important. Hence, this study aims to identify whether the video and audio of the given digital content are fake or real. For temporal video forgery detection, the convolutional 3D layers are used to build a model which can identify temporal forgeries with an average accuracy of 85% on the validation dataset. Also, the identification of audio forgery, using a ResNet-34 pre-trained model and the transfer learning approach, has been achieved. The proposed model achieves an accuracy of 99% with 0.3% validation loss on the validation part of the logical access dataset, which is better than earlier models in the range of 90-95% accuracy on the validation set.

Using Deep Learning Methods for Forensic Image and Video Investigation

2016

Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: https://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible.

Enhancement Digital Forensic Approach for Inter-Frame Video Forgery Detection Using a Deep Learning Technique

Iraqi Journal of Science

The digital world has been witnessing a fast progress in technology, which led to an enormous increase in using digital devices, such as cell phones, laptops, and digital cameras. Thus, photographs and videos function as the primary sources of legal proof in courtrooms concerning any incident or crime. It has become important to prove the trustworthiness of digital multimedia. Inter-frame video forgery one of common types of video manipulation performed in temporal domain. It deals with inter-frame video forgery detection that involves frame deletion, insertion, duplication, and shuffling. Deep Learning (DL) techniques have been proven effective in analysis and processing of visual media. Dealing with video data needs to handle the third dimension (the time dimension), which means extracting temporal features as well as spatial features. The proposed model is built based on the Three Dimension Convolution Neural Network (3D-CNN). Through pre-processing operation that introduced ...

Evaluation of Deep Learning and Conventional Approaches for Image Recaptured Detection in Multimedia Forensics

Mobile Information Systems

Image recaptured from a high-resolution LED screen or a good quality printer is difficult to distinguish from its original counterpart. The forensic community paid less attention to this type of forgery than to other image alterations such as splicing, copy-move, removal, or image retouching. It is significant to develop secure and automatic techniques to distinguish real and recaptured images without prior knowledge. Image manipulation traces can be hidden using recaptured images. For this reason, being able to detect recapture images becomes a hot research topic for a forensic analyst. The attacker can recapture the manipulated images to fool image forensic system. As far as we know, there is no prior research that has examined the pros and cons of up-to-date image recaptured techniques. The main objective of this survey was to succinctly review the recent outcomes in the field of image recaptured detection and investigated the limitations in existing approaches and datasets. The ...