FeatureBleed: Inferring Private Enriched Attributes From Sparsity-Optimized AI Accelerators
Year: 2026
Type: article
Abstract: Backend enrichmentis now widelydeployed in sensitive domains such as product recommendation pipelines, healthcare, and finance, where models are trained on confidential data and retrieve private features whose values influence inference behavior while remaining hidden from the API caller. This paper presents the firsthardware-level backend retrieval data-stealing attack, showing that accelerator optimizations designed for performance can directly undermine data confidentiality and bypass state-of-the-art privacy defenses. Our attack,FeatureBleed, exploitszero-skippingin AI accelerators to infer private backend-retrieved features solely through end-to-end timing, without relying on power analysis, DVFS manipulation, or shared-cache side channels. We evaluateFeatureBleedon three datasets spanning medical and non-medical domains—Texas-100X (clinical records), OrganAMNIST (medical imaging), and Census-19 (socioeconomic data). We further evaluateFeatureBleedacross three hardware backends (Intel AVX, Intel AMX, and NVIDIA A100) and three model architectures (DNNs, CNNs, and hybrid CNN–MLP pipelines), demonstrating that the leakage generalizes across CPU and GPU accelerators, data modalities, and application domains, with an adversarial advantage of up to98.87pp. Finally, we identify the root cause of the leakage as sparsity-driven zero-skipping in modern hardware. We quantify the privacy–performance–power trade-off: disabling zero-skipping increases Intel AMX's per-operation energy by up to25%and incurs100%performance overhead. We propose a padding-based defense that masks timing leakage by equalizing responses to the worst-case execution time, achieving protection with only7.24%average performance overhead and no additional power cost.
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G6115220380
OpenAlex ID: W7130716495