The paper proposes Voltron, a framework for executing large language model inferences on multiple user-end devices at the edge to achieve higher accuracy and satisfy QoS requirements.

This review comprehensively analyzes state-of-the-art decentralized trust and security mechanisms, concluding that while these approaches enhance privacy and resilience for IoT edge networks, challeng…

AgenTEE is a system that enables the secure, confidential execution of complex LLM agent pipelines directly on edge devices by using isolated confidential virtual machines.

This paper proposes EdgeFaaS, a function-based edge computing framework that abstracts distributed and heterogeneous physical resources and provides consistent virtual interfaces for deploying and exe…

The paper proposes CLASP, an end-to-end system with IMC acceleration for continual learning on edge platforms, addressing challenges of noisy computation and poor support for resource-efficient traini…

This paper proposes a new approach for real-time, dynamic and sound quantization and hardware to support it for resource-efficient neural networks and high-precision mathematics on edge devices, ensur…

This paper investigates Confused Deputy Attacks (CDAs) on AI Accelerators (AIAs) and finds that CDA is feasible on most major vendor AIAs, impacting a vast number of devices.

The paper proposes a trust-aware federated hybrid intrusion detection framework using multiple ML models at distributed edge nodes to proactively secure highly connected Intelligent Transport Systems.

The paper proposes CODA, an algorithm-hardware co-designed architecture for deploying Video Diffusion Models on edge devices, achieving up to 1.80x speedup and 1.74x energy efficiency.

This paper provides the first comprehensive review of threats and defenses specifically targeting on-device AI inference, revealing a significant imbalance where certain attack types, like adversarial…

This paper proposes SubEdge, a Net4AI subsystem for per-subscriber edge computing and communication resource provisioning, ensuring service continuity during mobility.

This paper investigates the latency performance of Mobile Edge Computing (MEC) on a 5G cellular network for real-time power transmission line analytics, demonstrating a low latency of 44.62 ms compare…

The paper proposes a framework to harvest unused computation resources on AI chips for general-purpose tasks using neural architecture search and approximation techniques.

This paper presents BenDi, an energy-efficient quasi-stochastic systolic architecture for bioelectronic systems on the edge.

This paper surveys how integrating Edge Computing, Machine Learning, and Deep Learning can enhance the security and resilience of complex Internet of Vehicles (IoV) networks.

The paper introduces SPARROW, an autonomous, open-source platform that uses solar power, edge AI, and satellite communication to enable continuous, scalable biodiversity monitoring in remote global ec…

The paper proposes a hybrid ASIC+eFPGA architecture to enhance the security and resilience of edge LLM inference accelerators against both runtime and supply-chain attacks.

The paper proposes a UEFI system utilizing SPDM to authenticate connected PCIe and USB devices, successfully demonstrating that this enhanced security mechanism introduces an acceptable processing ove…

This survey reviews hardware-rooted trust mechanisms, such as PUFs and TPMs, demonstrating that hardware-based solutions are superior to software-only methods for ensuring secure authentication and AI…