5 papers
Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting
Nicholas Carlini, Jorge Chávez-Saab, Anna Hambitzer +2
Deep neural networks (DNNs) are valuable assets, yet their public accessibility raises security concerns about parameter extraction by malicious actors. Recent work by Carlini et a…
Polynomial Time Cryptanalytic Extraction of Neural Network Models
Adi Shamir, Isaac Canales-Martinez, Anna Hambitzer +3
Billions of dollars and countless GPU hours are currently spent on training Deep Neural Networks (DNNs) for a variety of tasks. Thus, it is essential to determine the difficulty of…
Faulty isogenies: a new kind of leakage
Gora Adj, Jesús-Javier Chi-Domínguez, Víctor Mateu +1
In SIDH and SIKE protocols, public keys are defined over quadratic extensions of prime fields. We present in this work a projective invariant property characterizing affine Montgom…
Extending the GLS endomorphism to speed up GHS Weil descent using Magma
Jesús-Javier Chi-Domínguez, Francisco Rodríguez-Henríquez, Benjamin Smith
Let , and let be a generalized Galbraith--Lin--Scott (GLS) binary curve, with and .We show that the GLS endomorphis…
Stronger and Faster Side-Channel Protections for CSIDH
Daniel Cervantes-Vázquez, Mathilde Chenu, Jesús-Javier Chi-Domínguez +3
CSIDH is a recent quantum-resistant primitive based on the difficulty of finding isogeny paths between supersingular curves. Recently, two constant-time versions of CSIDH have been…