348 citations · 382 across the 10 of their papers we have counts for
3 papers · 1 filter
FBI: Fingerprinting models with Benign Inputs
Thibault Maho, Teddy Furon, Erwan Le Merrer
Recent advances in the fingerprinting of deep neural networks detect instances of models, placed in a black-box interaction scheme. Inputs used by the fingerprinting protocols are…
SurFree: a fast surrogate-free black-box attack
Thibault Maho, Teddy Furon, Erwan Le Merrer
Machine learning classifiers are critically prone to evasion attacks. Adversarial examples are slightly modified inputs that are then misclassified, while remaining perceptively cl…
Adversarial Frontier Stitching for Remote Neural Network Watermarking
Erwan Le Merrer, Patrick Perez, Gilles Trédan
The state of the art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requiremen…