João Marques-Silva

Catalan Institution for Research and Advanced Studies, University of Lleida

Papers on Lattice

Total citations

Topics

Research focus

Constitutional AI & AI Ethics (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Merkouris Papamichail (1)Konstantinos Varsos (1)Giorgos Flouris (1)

Papers (1)

Jun 22, 2026

Foundation for Reasearch and TechnologyJun 22, 2026·also Catalan Institution for Research and Advanced, University of Crete, University of Lleida

Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications

Apothem-optimal robustness certifications can be computed efficiently, yielding significant improvements over traditional volume-maximizing approaches.

Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris +1

Constitutional AI & AI Ethics Red-Teaming & Adversarial Robustness

João Marques-Silva

Research focus

Frequent co-authors

Papers (1)

Search

João Marques-Silva

Research focus

Frequent co-authors

Papers (1)