Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

O2, repositorio institucional de la UOC
Publication Contribución de congreso (ConferenceOutput)

Toward universal detector for synthesized images by estimating generative AI models

  • Seo, Ryota
  • Kuribayashi, Minoru
  • Ura, Akinobu
  • Mallet, Antoine
  • Cogranne, Rémi
  • Mazurczyk, Wojciech
  • Megias, David
One of the vulnerabilities in discriminators for AI-generated images is that the classification accuracy degrades when dealing with images generated using methods other than those they were trained on. As a countermeasure, in this study, we propose an image generation method estimator. The process of discrimination involves the input of an image to the estimator, which estimates the method used for its generation. Subsequently, a specialized fake image discriminator tailored to the estimated image generation method is used to identify the authenticity of the image. The activation functions are also considered according to the estimation results and analyzed for those discriminators. Discrimination scores are weighted and aggregated according to the estimation results, and the final decision is output. Our experimental results showed that the estimator achieved a classification accuracy of approximately 90% for 18 types of AI-generated images. Furthermore, by selecting the top two estimations in order of confidence, the accuracy increased to around 98%.
O2, repositorio institucional de la UOC
Publication Contribución de congreso (ConferenceOutput)

ZW-IDS: Zero-Watermarking-based network Intrusion Detection System using data provenance

  • Faraj, Omair
  • Megias, David
  • Garcia-Alfaro, Joaquin
In the rapidly evolving digital world, network security is a critical concern. Traditional security measures often fail to detect unknown attacks, making anomaly-based Network Intrusion Detection Systems (NIDS) using Machine Learning (ML) vital. However, these systems face challenges such as computational complexity and misclassification errors. This paper presents ZW-IDS, an innovative approach to enhance anomaly-based NIDS performance. We propose a two-layer classification NIDS integrating zero-watermarking with data provenance and ML. The first layer uses Support Vector Machines (SVM) with ensemble learning model for feature selection. The second layer generates unique zero-watermarks for each data packet using data provenance information. This approach aims to reduce false alarms, improve computational efficiency, and boost NIDS classification performance. We evaluate ZW-IDS using the CICIDS2017 dataset and compare its performance with other multi-method ML and Deep Learning (DL) solutions.
O2, repositorio institucional de la UOC
Publication Contribución de congreso (ConferenceOutput)

Toward the Selection of a Lightweight Authentication Technique for the Security of Smart Homes: Framework Architecture Based on a User Centric Design

  • Koohpayeh araghi, Tanya
  • Megias, David
  • Rosales, Andrea
The Internet of things (IoT) is known today as a substantial technology due to variety of its applications resulting in a huge circulation of users’ private information. Thus, it poses vital security concerns for the users of the IoT products. Consequently, preserving data integrity is a necessity in IoT applications. In this paper, we explore and analyze different existing techniques that countermeasure data integrity and authentication threats. The aim is to select the most lightweight and secure techniques to ensure data transmission in a proposed framework for smart homes and, more specifically, in smart meters data integrity. Our focus in this paper is on designing the different phases and the architecture of the proposed framework to preserve data integrity in the mentioned appliances. Moreover, the proposed framework follows a user centric design according to the people with cultural diversities from two different continents of Asia and Europe (Iran and Spain) in order to alleviate the user resistance against accepting this technology and designing a compatible system according to the users’ cultural varieties. To the best of our knowledge, less effort has been made in the field of secure data transmission in smart homes considering user’s security concerns by a multicultural approach. We believe that this research can be motivating and encouraging for the researchers and developers of IoT smart home appliances.
O2, repositorio institucional de la UOC
Publication Contribución de congreso (ConferenceOutput)

Single-image steganalysis in real-world scenarios based on classifier inconsistency detection

  • Lerch-Hostalot, Daniel
  • Megias, David
This paper presents an improved method for estimating the accuracy of a model based on images intended for prediction, enhancing the standard Detection of Classifier Inconsistencies (DCI) method. The conventional DCI method typically requires a large enough set of images from the same source to provide accurate estimations, which limits its practicality. Our enhanced approach overcomes this limitation by generating a set of images from a single original image, thereby enabling the application of the standard DCI method without requiring more than one target image. This method ensures that the generated images maintain the statistical properties of the original, preserving any embedded steganographic messages, through the use of non-destructive image manipulations such as flips, rotations, and shifts. Experimental results demonstrate that our method produces results comparable to those of the traditional DCI method, effectively estimating model accuracy with as few as 32 generated images. The robustness of our approach is also confirmed in challenging scenarios involving cover source mismatch (CSM), making it a viable solution for real-world applications.
O2, repositorio institucional de la UOC
Publication Contribución de congreso (ConferenceOutput)

Leveraging a Smart Grid Framework for Interoperability with a Distributed Ecosystem

  • Ferré-Queralt, Joan
  • Kabir, Farzana
  • Megias, David
  • Viejo, Alexandre
  • Castellà-Roca, Jordi
The transition from traditional, centralized power grids to decentralized smart grids is essential for integrating renewable energy sources and enhancing the efficiency, reliability, and sustainability of electricity production and distribution. This paper presents a comprehensive evaluation framework for a decentralized smart grid demonstrator, addressing key challenges such as interoperability, security, privacy, and scalability. The proposed architecture to perform the evaluation comprises three layers: user interface nodes (prosumers and smart meters), distribution nodes, and a master node, facilitating bidirectional electricity trading and communication. We implement this testing framework using a network of Raspberry Pi devices and a personal computer, simulating real-world smart grid conditions. The experimental evaluation, conducted with a dataset of household electricity consumption and production, confirms the system’s ability to simulate diverse user behaviors, maintain configurability, support various implementations, and ensure modularity and interoperability. Our results demonstrate the system’s effectiveness in providing a robust platform for evaluating different smart grid implementations, focusing on user anonymity, data integrity, system reliability, computational cost, and electricity consumption.