A high-speed multiple input multiple output (MIMO) wireless communication system is proposed for metro transportation. In order to better mitigate the inter-antenna interference (IAI) which degrades the quality of the MIMO receiver, we propose an efficient hybrid multiuser detection (MUD) technique. This approach consists of a two-stage procedure to achieve the optimum multiuser detector (OMD) by an acceptable computational complexity. The first stage performs interference cancellation by using sorted QR decomposition (SQRD), and the second stage performs the genetic algorithm (GA). It has two significant advantages: 1) The SQRD scheme provides "good initial setting knowledge" to improve the fitness of the population for GA. 2) The effect of fitness calculation is obtained from the QR decomposition (QRD) of a MIMO channel. Simulation results demonstrate that the two-stage procedure obtains a gain of 3 dB to 25 dB than other well-known MUD schemes. The computational complexity of the two-stage procedure can be reduced by 30% with QRD than other fitness calculation scheme in GA-MUD.Index Terms -multiple input multiple output, inter-antenna interference, multiuser detection, QR decomposition, genetic algorithm, evolutionary technique, optimization.
Obtaining a well-trained model involves expensive data collection and training procedures, therefore the model is a valuable intellectual property. Recent studies revealed that adversaries can `steal' deployed models even when they have no training samples and can not get access to the model parameters or structures. Currently, there were some defense methods to alleviate this threat, mostly by increasing the cost of model stealing. In this paper, we explore the defense from another angle by verifying whether a suspicious model contains the knowledge of defender-specified external features. Specifically, we embed the external features by tempering a few training samples with style transfer. We then train a meta-classifier to determine whether a model is stolen from the victim. This approach is inspired by the understanding that the stolen models should contain the knowledge of features learned by the victim model. We examine our method on both CIFAR-10 and ImageNet datasets. Experimental results demonstrate that our method is effective in detecting different types of model stealing simultaneously, even if the stolen model is obtained via a multi-stage stealing process. The codes for reproducing main results are available at Github (https://github.com/zlh-thu/StealingVerification).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.