SPARSEBLEED: Bypassing Attribute-Inference Defenses via Sparsity Optimizations

arXiv:2610.38110v1 Announce Type: new Abstract: Deep neural networks (DNNs) are widely deployed in safety- and privacy-critical domains such as healthcare and finance, where models are trained on confidential data. This paper presents the first hardware-level attribute-stealing attack that bypasses state-of-the-art privacy defenses, revealing that accelerator optimizations intended for performance can directly undermine data confidentiality.

Read the full article at arXiv cs.CR →