Noise-Aware Misclassification Attack Detection in Collaborative DNN Inference

ArXi:2603.17914v1 Announce Type: new 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.