3 papers
cs.CY2025
Vibe Learning: Education in the age of AI
Marcos Florencio, Francielle Prieto
The debate over whether "thinking machines" could replace human intellectual labor has existed in both public and expert discussions since the mid-twentieth century, when the conce…
cs.CR2025
Mechanistic Interpretability in the Presence of Architectural Obfuscation
Marcos Florencio, Thomas Barton
Architectural obfuscation - e.g., permuting hidden-state tensors, linearly transforming embedding tables, or remapping tokens - has recently gained traction as a lightweight substi…
cs.CR2025
An End-to-End Homomorphically Encrypted Neural Network
Marcos Florencio, Luiz Alencar, Bianca Lima
Every commercially available, state-of-the-art neural network consume plain input data, which is a well-known privacy concern. We propose a new architecture based on homomorphic en…