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.
Empowering edge intelligence: A comprehensive survey on on-device ai models
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
Router fine-tuning that biases MoE models toward short-term expert reuse improves cache locality, delivering 26% higher reuse and 1.77-1.99x decode speedup under memory constraints without inference-time overhead.
Unsupervised single-generation confidence calibration for reasoning LLMs via offline self-consistency proxy distillation outperforms baselines on math and QA tasks and improves selective prediction.
Edge AI systems require ongoing adaptation to evolving data and constraints to avoid violating budgets or losing reliability, formalized via an Agent-System-Environment lens that defines ten future research challenges.
Combining pruning, quantization, and early exits in CNNs reduces inference latency and memory on real edge devices with minimal accuracy loss.
Small language models can run RAG generation on-device without GPUs in reasonable time.
Cello Evaluator is a real-time postural feedback system for cellists running on current Android phones via on-device computer vision, validated as user-friendly by experts.
citing papers explorer
No citing papers match the current filters.