Full Program
Summary:
AI models face increasing security and privacy threats which compromise their integrity and reliability. While numerous AI-based methods have been proposed to detect and mitigate such risks, there remains a gap in systematizing this knowledge under a unified AI safety framework towards robust and resilient AI systems. This article proposes an attack-resilient framework that addresses both security and privacy threats against AI systems by integrating detection mechanisms, corrective actions, and explainable AI techniques. The proposed framework aims to equip AI systems with resilience strategies, improving defenses against evolving threats while ensuring reliability and compliance in high-stakes applications such as healthcare and GDPR-regulated environments.Author(s):
Efi Kafali
Centre for Research and Technology Hellas
Greece
Christoforos N. Spartalis
Centre for Research and Technology Hellas
Greece
Theodoros Semertzidis
Centre for Research and Technology Hellas
Greece
Charalampos Z. Patrikakis
University of West Attica, Egaleo
Greece
Petros Daras
Centre for Research and Technology Hellas
Greece