.png){kind=icon}
.png){kind=icon}
Return
Breaking Tiny Machine Learning: Why Quantized Neural Networks Need Domain-Specific Security Analysis
.png){kind=icon}
PRE
AI
DOI：10.1109/MM.2026.3666128.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Most tiny machine learning (TinyML) hardware focuses on supporting quantized neural networks (QNNs) to meet stringent constraints on power consumption, size, and cost. Despite this, the security aspects of quantization within TinyML hardware remain largely unexplored. Although previous studies indicate that QNNs demonstrate similar or enhanced robustness when compared to full-precision deep neural networks against typical evasion attacks, no attack strategies tailored specifically for TinyML hardware have been proposed yet. This article addresses the aforementioned shortfall by demonstrating how a two-step attack pipeline can surpass the current state of the art in the QNN context and shows the need for more hardware-aware security research.
Keywords:
Hardware
Tiny machine learning
Security
Quantization (signal)
Robustness
Perturbation methods
Glass box
Closed box
Pipelines
Computational modeling
Journal
IF:
2.9
Papers:
125
Citations:
2.7K