Uncovering and Understanding FPR Manipulation Attack in Industrial IoT Networks

ArXi:2601.14505v2 Announce Type: replace-cross In the network security domain, due to practical issues -- including imbalanced data and heterogeneous legitimate network traffic -- adversarial attacks in machine learning-based NIDSs have been viewed as attack packets misclassified as benign. Due to this prevailing belief, the possibility of (maliciously) perturbed benign packets being misclassified as attack has been largely ignored. In this paper, we nstrate that this is not only theoretically possible, but also a particular threat to.