A systematic review of on-device AI inference security finds defenses are imbalanced, with roughly half focused on IP theft while one-third of attacks (adversarial examples) lack any associated defenses.
Tiny machine learning and on-device inference: A survey of applications, challenges, and future directions.Sensors, 25(10):3191
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
BMRUs enable analog recurrent neural network hardware via discrete outputs that suppress noise 20-fold, with one-to-one parameter-to-circuit mapping and linear power scaling for recurrence.
A lightweight fully connected spiking neural network trigger with close-open postprocessing achieves 0.97 F1 on class-agnostic anomalous sound detection and enables 42.6x FLOPs reduction with improved error rate on sound event detection.
citing papers explorer
-
Protecting On-Device AI Inference: A Systematic Review of Attacks and Defence Mechanisms
A systematic review of on-device AI inference security finds defenses are imbalanced, with roughly half focused on IP theft while one-third of attacks (adversarial examples) lack any associated defenses.
-
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations
BMRUs enable analog recurrent neural network hardware via discrete outputs that suppress noise 20-fold, with one-to-one parameter-to-circuit mapping and linear power scaling for recurrence.
-
A Neuromorphic Trigger for Efficient Audio Event Detection
A lightweight fully connected spiking neural network trigger with close-open postprocessing achieves 0.97 F1 on class-agnostic anomalous sound detection and enables 42.6x FLOPs reduction with improved error rate on sound event detection.