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.
A comprehensive survey on hardware-aware neural architecture search
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.
A framework converts traditional edge tasks to NN models via NAS and schedules them on idle AI chips to improve performance without affecting primary workloads.
A multi-objective Bayesian optimization framework co-optimizes CIM crossbar hardware and DNN parameters for VGG8/CIFAR-10 and VGG16/Tiny-ImageNet, achieving comparable accuracy with up to 65% smaller area and 52% lower energy.
Demonstrates FLOPs-aware neural architecture search for hybrid quantum-classical neural networks to produce accurate yet computationally efficient models suitable for NISQ hardware.
A comprehensive survey of edge deep learning in computer vision and medical diagnostics that presents a novel categorization of hardware platforms by performance and usage scenarios.
elasticAI.explorer is an extensible framework for hardware-aware NAS supporting multiple search space types with YAML specs, code generation, cross-compilation, and on-device benchmarking.
A survey of Spiking Neural Network architecture search techniques viewed through a hardware/software co-design lens.
citing papers explorer
-
Hybrid Quantum-Classical Neural Architecture Search
Demonstrates FLOPs-aware neural architecture search for hybrid quantum-classical neural networks to produce accurate yet computationally efficient models suitable for NISQ hardware.