all InfoSec news
Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selection. (arXiv:2311.04588v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
Machine Learning (ML) models become vulnerable to Model Stealing Attacks
(MSA) when they are deployed as a service. In such attacks, the deployed model
is queried repeatedly to build a labelled dataset. This dataset allows the
attacker to train a thief model that mimics the original model. To maximize
query efficiency, the attacker has to select the most informative subset of
data points from the pool of available data. Existing attack strategies utilize
approaches like Active Learning and Semi-Supervised learning …
army attacker attacks box build dataset machine machine learning model extraction sample service stealing thief thieves train vulnerable