Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Manuel Eduardo Correia
  • Cluster

    Informática
  • Cargo

    Investigador Sénior
  • Desde

    01 janeiro 2009
004
Publicações

2021

Exposing Manipulated Photos and Videos in Digital Forensics Analysis

Autores
Ferreira, S; Antunes, M; Correia, ME;

Publicação
Journal of Imaging

Abstract
Tampered multimedia content is being increasingly used in a broad range of cybercrime activities. The spread of fake news, misinformation, digital kidnapping, and ransomware-related crimes are amongst the most recurrent crimes in which manipulated digital photos and videos are the perpetrating and disseminating medium. Criminal investigation has been challenged in applying machine learning techniques to automatically distinguish between fake and genuine seized photos and videos. Despite the pertinent need for manual validation, easy-to-use platforms for digital forensics are essential to automate and facilitate the detection of tampered content and to help criminal investigators with their work. This paper presents a machine learning Support Vector Machines (SVM) based method to distinguish between genuine and fake multimedia files, namely digital photos and videos, which may indicate the presence of deepfake content. The method was implemented in Python and integrated as new modules in the widely used digital forensics application Autopsy. The implemented approach extracts a set of simple features resulting from the application of a Discrete Fourier Transform (DFT) to digital photos and video frames. The model was evaluated with a large dataset of classified multimedia files containing both legitimate and fake photos and frames extracted from videos. Regarding deepfake detection in videos, the Celeb-DFv1 dataset was used, featuring 590 original videos collected from YouTube, and covering different subjects. The results obtained with the 5-fold cross-validation outperformed those SVM-based methods documented in the literature, by achieving an average F1-score of 99.53%, 79.55%, and 89.10%, respectively for photos, videos, and a mixture of both types of content. A benchmark with state-of-the-art methods was also done, by comparing the proposed SVM method with deep learning approaches, namely Convolutional Neural Networks (CNN). Despite CNN having outperformed the proposed DFT-SVM compound method, the competitiveness of the results attained by DFT-SVM and the substantially reduced processing time make it appropriate to be implemented and embedded into Autopsy modules, by predicting the level of fakeness calculated for each analyzed multimedia file.

2021

A Dataset of Photos and Videos for Digital Forensics Analysis Using Machine Learning Processing

Autores
Ferreira, S; Antunes, M; Correia, ME;

Publicação
Data

Abstract
Deepfake and manipulated digital photos and videos are being increasingly used in a myriad of cybercrimes. Ransomware, the dissemination of fake news, and digital kidnapping-related crimes are the most recurrent, in which tampered multimedia content has been the primordial disseminating vehicle. Digital forensic analysis tools are being widely used by criminal investigations to automate the identification of digital evidence in seized electronic equipment. The number of files to be processed and the complexity of the crimes under analysis have highlighted the need to employ efficient digital forensics techniques grounded on state-of-the-art technologies. Machine Learning (ML) researchers have been challenged to apply techniques and methods to improve the automatic detection of manipulated multimedia content. However, the implementation of such methods have not yet been massively incorporated into digital forensic tools, mostly due to the lack of realistic and well-structured datasets of photos and videos. The diversity and richness of the datasets are crucial to benchmark the ML models and to evaluate their appropriateness to be applied in real-world digital forensics applications. An example is the development of third-party modules for the widely used Autopsy digital forensic application. This paper presents a dataset obtained by extracting a set of simple features from genuine and manipulated photos and videos, which are part of state-of-the-art existing datasets. The resulting dataset is balanced, and each entry comprises a label and a vector of numeric values corresponding to the features extracted through a Discrete Fourier Transform (DFT). The dataset is available in a GitHub repository, and the total amount of photos and video frames is 40,588 and 12,400, respectively. The dataset was validated and benchmarked with deep learning Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) methods; however, a plethora of other existing ones can be applied. Generically, the results show a better F1-score for CNN when comparing with SVM, both for photos and videos processing. CNN achieved an F1-score of 0.9968 and 0.8415 for photos and videos, respectively. Regarding SVM, the results obtained with 5-fold cross-validation are 0.9953 and 0.7955, respectively, for photos and videos processing. A set of methods written in Python is available for the researchers, namely to preprocess and extract the features from the original photos and videos files and to build the training and testing sets. Additional methods are also available to convert the original PKL files into CSV and TXT, which gives more flexibility for the ML researchers to use the dataset on existing ML frameworks and tools.

2020

Profiling IT security and interoperability in Brazilian health organisations from a business perspective

Autores
Rui, RJ; Martinho, R; Oliveira, AA; Alves, D; Nogueira Reis, ZSN; Santos Pereira, C; Correia, ME; Antunes, LF; Cruz Correia, RJ;

Publicação
International Journal of E-Health and Medical Communications

Abstract
The proliferation of electronic health (e-Health) initiatives in Brazil over the last 2 decades has resulted in a considerable fragmentation within health information technology (IT), with a strong political interference. The problem regarding this issue became twofold: 1) there are considerable flaws regarding interoperability and security involving patient data; and 2) it is difficult even for an experienced company to enter the Brazilian health IT market. In this article, the authors aim to assess the current state of IT interoperability and security in hospitals in Brazil and evaluate the best business strategy for an IT company to enter this difficult but very promising health IT market. A face-to-face questionnaire was conducted among 11 hospital units to assess their current status regarding IT interoperability and security aspects. Global Brazilian socio-economic data was also collected, and helped to not only identify areas of investment regarding health IT security and interoperability, but also to derive a business strategy, composed out of recommendations listed in the paper. Copyright © 2020, IGI Global.

2020

Illegitimate HIS access by healthcare professionals detection system applying an audit trail-based model

Autores
Sa Correia, L; Correia, ME; Cruz Correia, R;

Publicação
HEALTHINF 2020 - 13th International Conference on Health Informatics, Proceedings; Part of 13th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2020

Abstract
Complex data management on healthcare institutions makes very hard to identify illegitimate accesses which is a serious issue. We propose to develop a system to detect accesses with suspicious behavior for further investigation. We modeled use cases (UC) and sequence diagrams (SD) showing the data flow between users and systems. The algorithms represented by activity diagrams apply rules based on professionals' routines, use data from an audit trail (AT) and classify accesses as suspicious or normal. The algorithms were evaluated between 23rd and 31st July 2019. The results were analyzed using absolute and relative frequencies and dispersion measures. Access classification was in accordance to rules applied. "Check time of activity" UC had 64, 78% of suspicious classifications, being 55% of activity period shorter and 9, 78% longer than expected, "Check days of activity" presented 2, 27% of suspicious access and "EHR read access" 79%, the highest percentage of suspicious accesses. The results show the first picture of HIS accesses. Deeper analysis to evaluate algorithms sensibility and specificity should be done. Lack of more detailed information about professionals' routines and systems, and low quality of systems logs are some limitations. Although we believe this is an important step in this field.

2020

Providing Secured Access Delegation in Identity Management Systems

Autores
Shehu, AS; Pinto, A; Correia, ME;

Publicação
Proceedings of the 17th International Joint Conference on e-Business and Telecommunications, ICETE 2020 - Volume 2: SECRYPT, Lieusaint, Paris, France, July 8-10, 2020.

Abstract

Teses
supervisionadas

2020

Establishing Trust and Confidence Among Entities in Distributed Networks

Autor
Francis Nwebonyi Nwebonyi

Instituição
UP-FCUP

2019

Establishing Trust and Confidence Among Entities in Distributed Networks

Autor
Francis Nwebonyi Nwebonyi

Instituição
UP-FCUP

2018

Infrastructure for Identity Management, Authentication and Authorization

Autor
Muhammad Shehu Abubakar-Sadiq

Instituição
UP-FCUP

2018

Authentication modules for Keycloak authentication server

Autor
Daicy Patricia Duarte Paiva

Instituição
UP-FCUP

2017

A flexible framework for Rogue Access Point detection

Autor
Ricardo Jorge Esteves Gonçalves

Instituição
UP-FCUP