Search Results for author:
Found 5 papers, 1 papers with code
ACTIVETHIEF: Model Extraction Using Active Learning and Unannotated Public Data
We demonstrate that (1) it is possible to use ACTIVETHIEF to extract deep classifiers trained on a variety of datasets from image and text domains, while querying the model with as few as 10-30% of samples from public datasets, (2) the resulting model exhibits a higher transferability success rate of adversarial examples than prior work, and (3) the attack evades detection by the state-of-the-art model extraction detection method, PRADA.
A framework for the extraction of Deep Neural Networks by leveraging public data
Machine learning models trained on confidential datasets are increasingly being deployed for profit.
A case for multiple and parallel RRAMs as synaptic model for training SNNs
As a solution, we propose the use of multiple PCMO-RRAMs in parallel within a synapse.
An On-chip Trainable and Clock-less Spiking Neural Network with 1R Memristive Synapses
This enables learning and recognition simultaneously on an SNN.
A Software-equivalent SNN Hardware using RRAM-array for Asynchronous Real-time Learning
Spiking Neural Network (SNN) naturally inspires hardware implementation as it is based on biology.
