Efthimia Kafali

According to our database, Efthimia Kafali authored at least 6 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Dynamic Trade-Offs in Adversarial Training: Exploring Efficiency, Robustness, Forgetting, and Interpretability.

Efi Kafali, Theodoros Semertzidis, Petros Daras

Neural Process. Lett., June, 2025

Designing AI Systems with Correction Mechanisms Towards Attack-Resilient Architectures.

Efi Kafali, Christoforos N. Spartalis, Theodoros Semertzidis, Charalampos Z. Patrikakis, Petros Daras

Proceedings of the IEEE International Conference on Cyber Security and Resilience, 2025

2024

Defending Against AI Threats with a User-Centric Trustworthiness Assessment Framework.

Efi Kafali, Davy Preuveneers, Theodoros Semertzidis, Petros Daras

Big Data Cogn. Comput., 2024

Building a Use Case-Driven Adversarial Threat Matrix: A Comprehensive Approach.

Prodromos Kiriakidis, Efi Kafali, Georgios Rizos, Antonis Voulgaridis, Theodoros Semertzidis, Stephane Gazut, Petros Daras, Konstantinos Votis

Proceedings of the IEEE International Conference on Cyber Security and Resilience, 2024

2021

Delayed Adversarial Training with Non-Sequential Adversarial Epochs.

Efi Kafali, Theodoros Semertzidis, Petros Daras

Proceedings of the 33rd IEEE International Conference on Tools with Artificial Intelligence, 2021

2020

RobusterNet: Improving Copy-Move Forgery Detection with Volterra-based Convolutions.

Efthimia Kafali, Nicholas Vretos, Theodoros Semertzidis, Petros Daras

Proceedings of the 25th International Conference on Pattern Recognition, 2020