7 papers
AgenTEE: Confidential LLM Agent Execution on Edge Devices
Sina Abdollahi, Mohammad M Maheri, Javad Forough +5
Large Language Model (LLM) agents provide powerful automation capabilities, but they also create a substantially broader attack surface than traditional applications due to their t…
Towards Real-Time ECG and EMG Modeling on NPUs
Josh Millar, Ashok Samraj Thangarajan, Soumyajit Chatterjee +1
The miniaturisation of neural processing units (NPUs) and other low-power accelerators has enabled their integration into microcontroller-scale wearable hardware, supporting near-r…
Benchmarking Ultra-Low-Power NPUs
Josh Millar, Yushan Huang, Sarab Sethi +2
Efficient on-device neural network (NN) inference offers predictable latency, improved privacy and reliability, and lower operating costs for vendors than cloud-based inference. Th…
An Architecture for Spatial Networking
Josh Millar, Ryan Gibb, Roy Ang +2
Physical spaces are increasingly dense with networked devices, promising seamless coordination and ambient intelligence. Yet today, cloud-first architectures force all communicatio…
Steps towards an Ecology for the Internet
Anil Madhavapeddy, Sam Reynolds, Alec P. Christie +10
The Internet has grown from a humble set of protocols for end-to-end connectivity into a critical global system with no builtin "immune system". In the next decade the Internet wil…
Energy-Aware Deep Learning on Resource-Constrained Hardware
Josh Millar, Hamed Haddadi, Anil Madhavapeddy
The use of deep learning (DL) on Internet of Things (IoT) and mobile devices offers numerous advantages over cloud-based processing. However, such devices face substantial energy c…