all InfoSec news
DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks
May 24, 2024, 4:12 a.m. | Patrik Vel\v{c}ick\'y, Jakub Breier, Xiaolu Hou, Mladen Kova\v{c}evi\'c
cs.CR updates on arXiv.org arxiv.org
Abstract: Fault injection attacks are a potent threat against embedded implementations of neural network models. Several attack vectors have been proposed, such as misclassification, model extraction, and trojan/backdoor planting. Most of these attacks work by flipping bits in the memory where quantized model parameters are stored.
In this paper, we introduce an encoding-based protection method against bit-flip attacks on neural networks, titled DeepNcode. We experimentally evaluate our proposal with several publicly available models and datasets, by …
arxiv attack attacks attack vectors backdoor bits cs.ai cs.cr embedded encoding extraction flip injection injection attacks memory model extraction network networks neural network neural networks protection threat trojan work
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Ingénieur Développement Logiciel IoT H/F
@ Socomec Group | Benfeld, Grand Est, France
Architecte Cloud – Lyon
@ Sopra Steria | Limonest, France
Senior Risk Operations Analyst
@ Visa | Austin, TX, United States
Military Orders Writer
@ Advanced Technology Leaders, Inc. | Ft Eisenhower, GA, US
Senior Golang Software Developer (f/m/d)
@ E.ON | Essen, DE
Senior Revenue Operations Analyst (Redwood City)
@ Anomali | Redwood City, CA