Athanasia Kollarou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Athanasia Kollarou has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Vasileios Gkioulos
Norwegian University of Science and Technology (NTNU)
2 shared publications - Apostolis Zarras
Department of Digital Systems, University of Piraeus, Piraeus, Greece
1 shared publication Aristeidis Farao
InQbit Innovations SRL, Bucharest, Romania
1 shared publicationChristos Xenakis
University of Piraeus, Piraeus, Greece
1 shared publication- Georgios Spathoulas
Department of Information Security and Communication Technology, Norwegian University of Science and Technology (NTNU), Gjøvik, Norway
1 shared publication - Jia-Chun Lin
Department of Information Security and Communication Technology, Norwegian University of Science and Technology, Gjøvik, Norway
1 shared publication
Latest Publications
- Open Access
- 26 September 2026
- Published by Springer Nature in International Journal of Information Security
- Vol. 25 (6) , 168
Towards Deployable Anomaly Detection in industrial CPS/ICS: A Survey and Deployability Assessment
- 26 September 2026
- Published by Springer Nature in International Journal of Information Security
- Vol. 25 (6) , 168
Open AccessTowards Deployable Anomaly Detection in industrial CPS/ICS: A Survey and Deployability Assessment
- 3 June 2026
- Published by Springer Nature
- p. 243-256
ICSSPulse: A Modular LLM-Assisted Platform for Industrial Control System Penetration Testing
- 3 June 2026
- Published by Springer Nature
- p. 243-256
ICSSPulse: A Modular LLM-Assisted Platform for Industrial Control System Penetration Testing
- Open Access
- 31 October 2025
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e3330
Testing the limits: exploring adversarial techniques in AI models
The rising adoption of artificial intelligence and machine learning in critical sectors underscores the pressing need for robust systems capable of withstanding adversarial threats. While deep learning architectures have revolutionized tasks such as image recognition, their susceptibility to adversarial techniques remains an open challenge. This article evaluates the impact of various adversarial methods, including the fast gradient sign method, projected gradient descent, DeepFool, and Carlini & Wagner, on five neural network models: a fully connected neural network, LeNet, Simple convolutional neural network (CNN), MobileNetV2, and VGG11. Using the E V AI SION tool explicitly developed for this research, these attacks were implemented and analyzed based on accuracy, F1-score, and misclassification rate. The results revealed varying levels of vulnerability across the tested models, with simpler architectures occasionally outperforming more complex ones. These findings emphasize the importance of selecting the most appropriate adversarial technique for a given architecture and customizing the associated attack parameters to achieve optimal results in each scenario.
- 31 October 2025
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e3330
Open AccessTesting the limits: exploring adversarial techniques in AI models
The rising adoption of artificial intelligence and machine learning in critical sectors underscores the pressing need for robust systems capable of withstanding adversarial threats. While deep learning architectures have revolutionized tasks such as image recognition, their susceptibility to adversarial techniques remains an open challenge. This article evaluates the impact of various adversarial methods, including the fast gradient sign method, projected gradient descent, DeepFool, and Carlini & Wagner, on five neural network models: a fully connected neural network, LeNet, Simple convolutional neural network (CNN), MobileNetV2, and VGG11. Using the E V AI SION tool explicitly developed for this research, these attacks were implemented and analyzed based on accuracy, F1-score, and misclassification rate. The results revealed varying levels of vulnerability across the tested models, with simpler architectures occasionally outperforming more complex ones. These findings emphasize the importance of selecting the most appropriate adversarial technique for a given architecture and customizing the associated attack parameters to achieve optimal results in each scenario.
- 10 August 2025
- Published by Springer Nature
- p. 239-253
Data Poisoning in FL: Clipping Malicious Updates
- 10 August 2025
- Published by Springer Nature
- p. 239-253
Data Poisoning in FL: Clipping Malicious Updates