Anna Hambitzer

Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting

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 al. (crypto'20)...

Polynomial Time Cryptanalytic Extraction of Neural Network Models

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 extracting all...

Exploring Temporal Information Dynamics in Spiking Neural Networks

Most existing Spiking Neural Network (SNN) works state that SNNs may utilize temporal information dynamics of spikes. However, an explicit analysis of temporal information dynamics is still...

Workload-Balanced Pruning for Sparse Spiking Neural Networks

Pruning for Spiking Neural Networks (SNNs) has emerged as a fundamental methodology for deploying deep SNNs on resource-constrained edge devices. Though the existing pruning methods can provide...

Generic Partial Decryption as Feature Engineering for Neural Distinguishers

CLAASPing ARADI: Automated Analysis of the ARADI Block Cipher

Polynomial Time Cryptanalytic Extraction of Neural Network Models

Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting

Deep Neural Cryptography

NNBits: Bit Profiling with a Deep Learning Ensemble Based Distinguisher

Exploring Temporal Information Dynamics in Spiking Neural Networks

GPU4SNN: GPU-Based Acceleration for Spiking Neural Network Simulations

Limitations of the Use of Neural Networks in Black Box Cryptanalysis