all InfoSec news
Poster: Sponge ML Model Attacks of Mobile Apps. (arXiv:2303.01243v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
Machine Learning (ML)-powered apps are used in pervasive devices such as
phones, tablets, smartwatches and IoT devices. Recent advances in
collaborative, distributed ML such as Federated Learning (FL) attempt to solve
privacy concerns of users and data owners, and thus used by tech industry
leaders such as Google, Facebook and Apple. However, FL systems and models are
still vulnerable to adversarial membership and attribute inferences and model
poisoning attacks, especially in FL-as-a-Service ecosystems recently proposed,
which can enable attackers to …
adversarial apple apps attacks data devices distributed facebook federated learning google industry iot iot devices leaders machine machine learning ml model mobile mobile apps phones poisoning privacy smartwatches systems tech tech industry vulnerable