Edge-Cloud Collaborative Inference

Follow this topic Ask about this topic

Latest papers

34 papers12 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Noise-Aware Misclassification Attack Detection in Collaborative DNN Inference
Mar 18, 2026Shima Yousefi, Saptarshi DebroyAdversarial Example Detection Anomaly Detection
City University of New York
Ruyi2.5 Technical Report
Mar 18, 2026Huan Song, Shuyu Tian, Qingfei Zhao +5Edge-Cloud Collaborative Inference Multimodal Foundation Models
Institute of Artificial Intelligence (TeleAI), China Telecom
Edge-Cloud Collaborative Speech Emotion Captioning via Token-Level Speculative Decoding in Audio-Language Models
Mar 12, 2026Xiangyuan Xue, Jiajun Lu, Yan Gao +3Edge-Cloud Collaborative Inference Speculative Decoding
The University of Auckland, New Zealand · The University of Melbourne, Australia · The University of Cambridge, United Kingdom +1
ActECC: Action Chunk Temporal Harnessing for Edge-Cloud Collaborative VLA Inference System
Mar 9, 2026Zihao Zheng, Zhihao Mao, Hui Huang +9Temporal Modeling for VLA Models Edge-Cloud Collaborative Inference
School of Computer Science, Peking University, Beijing, China. · School of Artificial Intelligence, Beijing Normal University, Beijing, China. · School of Software Engineering, South China University of Technology, Guangzhou, China.

Mar 18, 2026J/K move · Enter open · S save

Noise-Aware Misclassification Attack Detection in Collaborative DNN Inference

Shima Yousefi, Saptarshi Debroy

City University of New York

Adversarial Example Detection Anomaly Detection Edge Inference Edge-Cloud Collaborative Inference

Open paper AskPDF arXiv

Collaborative inference of object classification Deep neural Networks (DNNs) where resource-constrained end-devices offload partially processed data to remote edge servers to complete end-to-end processing, is becoming a key enabler of edge-AI. However, such edge-offloading is vulnerable to malicious data injections leading to stealthy misclassifications that are tricky to detect, especially in the presence of environmental noise. In this paper, we propose a semi-gray-box and noise- aware anomaly detection framework fueled by a variational autoencoder (VAE) to capture deviations caused by adversarial manipulation. The proposed framework incorporates a robust noise-aware feature that captures the characteristic behavior of environmental noise to improve detection accuracy while reducing false alarm rates. Our evaluation with popular object classification DNNs demonstrate the robustness of the proposed detection (up to 90% AUROC across DNN configurations) under realistic noisy conditions while revealing limitations caused by feature similarity and elevated noise levels.

Latest papers

Noise-Aware Misclassification Attack Detection in Collaborative DNN Inference

Ruyi2.5 Technical Report

Edge-Cloud Collaborative Speech Emotion Captioning via Token-Level Speculative Decoding in Audio-Language Models

ActECC: Action Chunk Temporal Harnessing for Edge-Cloud Collaborative VLA Inference System