Scholarly Works
Research Output
Recent Publications
Cybersecurity training and healthcare: the AERAS approach
Publishing year: 2024
Journal article
International Journal of Information Security, 2024, Volume 23, Issue 2
Repository
Cyber ranges have gained significant importance in cybersecurity training in recent years, and they are still playing a role of paramount importance, thanks to their ability to give trainees hands-on experience with real-world exercises. This paper presents the motivation and objective of the AERAS project, including a thorough analysis of data from ad hoc interviews and surveys specifically designed and administered for the project’s goals. AERAS aims to apply the cyber range concept to the critical healthcare sector. The AERAS platform will be a virtual cyberwarfare solution that will simulate the operation and effects of security controls and offer hands-on training on their development, assessment, use, and management.
Privacy-Preserving Online Content Moderation: A Federated Learning Use Case
Publishing year: 2023
Journal article
ACM Web Conference 2023 - Companion of the World Wide Web Conference, 2023
Repository
Pages 280-289
Users are exposed to a large volume of harmful content that appears daily on various social network platforms. One solution to users' protection is developing online moderation tools using Machine Learning (ML) techniques for automatic detection or content filtering. On the other hand, the processing of user data requires compliance with privacy policies. In this paper, we propose a framework for developing content moderation tools in a privacy-preserving manner where sensitive information stays on the users' device. For this purpose, we apply Differentially Private Federated Learning (DP-FL), where the training of ML models is performed locally on the users' devices, and only the model updates are shared with a central entity. To demonstrate the utility of our approach, we simulate harmful text classification on Twitter data in a distributed FL fashion- but the overall concept can be generalized to other types of misbehavior, data, and platforms. We show that the performance of the proposed FL framework can be close to the centralized approach - for both the DP-FL and non-DP FL. Moreover, it has a high performance even if a small number of clients (each with a small number of tweets) are available for the FL training. When reducing the number of clients (from fifty to ten) or the tweets per client (from 1K to 100), the classifier can still achieve AUC. Furthermore, we extend the evaluation to four other Twitter datasets that capture different types of user misbehavior and st...
Privacy-Preserving Online Content Moderation with Federated Learning
Publishing year: 2023
Conference paper
ACM Web Conference, 2023
Repository
Pages 1335-1338
Users are exposed to a large volume of harmful content that appears daily on various social network platforms. One solution to users' protection is developing online moderation tools using Machine Learning (ML) techniques for automatic detection or content filtering. On the other hand, the processing of user data requires compliance with privacy policies. This paper proposes a privacy-preserving Federated Learning (FL) framework for online content moderation that incorporates Central Differential Privacy (CDP). We simulate the FL training of a classifier for detecting tweets with harmful content, and we show that the performance of the FL framework can be close to the centralized approach. Moreover, it has a high performance even if a small number of clients (each with a small number of tweets) are available for the FL training. When reducing the number of clients (from fifty to ten) or the tweets per client (from 1K to 100), the classifier can still achieve AUC. Furthermore, we extend the evaluation to four other Twitter datasets that capture different types of user misbehavior and still obtain a promising performance (61% - 80% AUC).
Identifying Misinformation on YouTube through Transcript Contextual Analysis with Transformer Models
Publishing year: 2023
Journal article
arXiv preprint arXiv:2307.12155, 2023, 2023
Google Scholar
Misinformation on YouTube is a significant concern, necessitating robust detection strategies. In this paper, we introduce a novel methodology for video classification, focusing on the veracity of the content. We convert the conventional video classification task into a text classification task by leveraging the textual content derived from the video transcripts. We employ advanced machine learning techniques like transfer learning to solve the classification challenge. Our approach incorporates two forms of transfer learning: (a) fine-tuning base transformer models such as BERT, RoBERTa, and ELECTRA, and (b) few-shot learning using sentence-transformers MPNet and RoBERTa-large. We apply the trained models to three datasets: (a) YouTube Vaccine-misinformation related videos, (b) YouTube Pseudoscience videos, and (c) Fake-News dataset (a collection of articles). Including the Fake-News dataset extended the evaluation of our approach beyond YouTube videos. Using these datasets, we evaluated the models distinguishing valid information from misinformation. The fine-tuned models yielded Matthews Correlation Coefficient>0.81, accuracy>0.90, and F1 score>0.90 in two of three datasets. Interestingly, the few-shot models outperformed the fine-tuned ones by 20% in both Accuracy and F1 score for the YouTube Pseudoscience dataset, highlighting the potential utility of this approach -- especially in the context of limited training data.
HyperGraphDis: Leveraging Hypergraphs for Contextual and Social-Based Disinformation Detection
Publishing year: 2023
Journal article
arXiv preprint arXiv:2310.01113, 2023, 2023
Google Scholar
In light of the growing impact of disinformation on social, economic, and political landscapes, accurate and efficient identification methods are increasingly critical. This paper introduces HyperGraphDis, a novel approach for detecting disinformation on Twitter that employs a hypergraph-based representation to capture (i) the intricate social structures arising from retweet cascades,(ii) relational features among users, and (iii) semantic and topical nuances. Evaluated on four Twitter datasets--focusing on the 2016 US presidential election and the COVID-19 pandemic--HyperGraphDis outperforms existing methods in both accuracy and computational efficiency, underscoring its effectiveness and scalability for tackling the challenges posed by disinformation dissemination. HyperGraphDis displays exceptional performance on a COVID-19-related dataset, achieving an impressive F1 score (weighted) of approximately 89.5%. This result represents a notable improvement of around 4% compared to the other state-of-the-art methods. Additionally, significant enhancements in computation time are observed for both model training and inference. In terms of model training, completion times are accelerated by a factor ranging from 2.3 to 7.6 compared to the second-best method across the four datasets. Similarly, during inference, computation times are 1.3 to 6.8 times faster than the state-of-the-art.
A Qualitative Analysis of Illicit Arms Trafficking on Darknet Marketplaces
Publishing year: 2023
Conference paper
ACM International Conference Proceeding Series, 2023
Repository
During the last decade, the dark web has become the playground for criminal and underground activities, such as marketplaces of drugs and guns, as well as illegal content sharing. The dark web is one of the top crime environments presented in EUROPOL's Internet Organised Crime Threat Assessment 2021. This paper provides a qualitative study on the darknet marketplaces of illegal arms trafficking. For this purpose, we implemented a crawler based on the ACHE Python library to collect hidden web pages (onion services) on the Tor network. We gathered data from ten marketplaces recommended by dark web search engines - Ahmia, Deep Search, and Onion Land Search. We provide a first report of the overall landscape of illicit arms trafficking, discussing the range of weapons such as military drones, explosives, and other related products, together with the payment and shipping methods provided by the vendors. The findings verify previous reports from reputable institutions (United Nations and RAND Europe). Most of these illicit marketplaces are easily accessible to the average user; they are well-organized with a large variety of firearms and also provide extensive customer support.
8
Unique publications
50%
Open access (4 publications; 3 without information)
62.5%
With other institutions (5 publications; 3 without information)
H-Index Reports
| Index type | Scopus | Google Scholar | Web of Science |
|---|---|---|---|
| H-index | 4 | 6 | 0 |
| H5-index | 4 | 6 | 0 |
| H10-index | 4 | 6 | 0 |
Publications per year and source
No description yet.
- Faculty
- Faculty of Engineering and Technology
- Department
- Department of Electrical Engineering, Computer Engineering and Informatics
- Title
- Special Scientist-Researcher