This repository curates open-access research publications that are closely related to the project’s focus on secure and resilient AI. These resources support the project’s goals by providing foundational knowledge, state-of-the-art insights, and critical analysis from the broader research community.
To support targeted exploration, the publications are divided into three categories:
Surveys: In-depth reviews and meta-analyses that synthesize the current state of research in secure and resilient AI, outlining methodologies, taxonomies, and open research directions.
- Attacks and Defenses: Publications analyzing threats to AI systems and presenting mitigation strategies, with a focus on adversarial robustness, detection techniques, and trustworthy AI design.
Ethics: Research addressing the ethical, legal, and societal implications of AI, including topics such as fairness, transparency, accountability, and compliance with policy frameworks.