Ilias Politis
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This systematic literature review analyzes existing methods, models, and instruments for assessing human vulnerability in cybersecurity, concluding that current approaches are fragmented and lack a dynamic, holistic view of human risk.
The paper proposes a kernel-based, polynomial approximation of the ReLU activation function to enable the use of non-linear deep learning models, such as LLMs, within the constraints of Homomorphic Encryption (HE) for privacy-preserving computation.
Papers
Kernel-Based ReLU Approximation for Homomorphic Encryption-Compatible Privacy-preserving Deep Learning Models
The paper proposes a kernel-based, polynomial approximation of the ReLU activation function to enable the use of non-linear deep learning models, such as LLMs, within the constraints of Homomorphic En…