An official website of the United States government
The accurate identification of wireless devices is critical for enabling automated network access monitoring and authenticated data communication in large-scale networks; e.g., IoT networks. RF fingerprinting has emerged as a potential solution for device identification by leveraging the transmitter unique manufacturing impairments of the RF components. Although deep learning is proven efficient in classifying devices based on the hardware impairments, trained models perform poorly due to channel variations. That is, although training and testing neural networks using data generated during the same period achieve reliable classification, testing them on data generated at different times degrades the accuracy substantially. To the best of our knowledge, we are the first to propose to leverage MIMO capabilities to mitigate the channel effect and provide a channelresilient device classification. For the proposed technique we show that, for Rayleigh channels, blind partial channel estimation enabled by MIMO increases the testing accuracy by up to 40% when the models are trained and tested over the same channel, and by up to 60% when the models are tested on a channel that is different from that used for training.
more »
« less
Deep Learning-Based Visibility Region Classification for Extra-Large Aperture Arrays
Spatial non wide-sense stationarities cause partial visibility regions (VRs), and it is a unique propagation characteristic of emerging extra-large aperture arrays (ELAAs). Thus, classification of VRs is a necessity for accurate estimation of channels and efficient design of VR-aware precoders for ELAAs. In this paper, a deep learning framework is proposed to classify VRs in ELAAs. Our objective is to boost the accuracy of classifying VRs based on the uplink pilots received at the ELAAs. Consequently, we focus on guaranteeing user-fairness in the presence of wholly/partial VRs and improving the achievable rates by adopting VR-aware channel estimation and precoding. We propose a hybrid deep learning architecture comprising one dimensional convolutional neural networks and long-short term memory to classify VRs of each user at the ELAA. To achieve a higher accuracy, we generate a diverse dataset through Monte-Carlo simulations that captures numerous combinations of VRs at the ELAA. A transmit power allocation algorithm is also proposed to achieve a common downlink rate for all users irrespective of the different VRs, and its computational complexity is discussed. A set of numerical results is presented to evaluate the performance of our proposed framework. It is efficient and accurate in classifying VRs. Thus, it can be used to enhance the estimation accuracy of ELAA channels with VRs and thereby to design VR-aware precoders to boost spectral/energy efficiency of the next-generation wireless systems.
more »
« less
- Award ID(s):
- 2326621
- PAR ID:
- 10652287
- Publisher / Repository:
- IEEE
- Date Published:
- Page Range / eLocation ID:
- 4774 to 4779
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The performance of integrated sensing and communications (ISAC) empowered intelligent reflecting surface (IRS)aided massive multiple-input multiple-output (MIMO) systems operating over spatially correlated Rician fading is investigated. Computationally-efficient linear precoders are used to construct the ISAC signal by invoking the maximal ratio transmission (MRT) criterion into the composite channels containing both direct and IRS reflected channels. The uplink communication channels are estimated based on the linear minimum mean square error criterion and used to construct user precoders. The IRS phase-shifts are optimized based on the statistical channel knowledge to maximize the minimum average power gains of the composite communication channels subject to an average power threshold for the reflected sensing channel. The communication performance is evaluated by deriving the achievable user rates, while the sensing performance is studies by locating the target via the 2D MUltiple SIgnal Classification (MUSIC) algorithm. Our numerical results are used to study the trade-off between the communication and sensing performance metrics in IRS-aided massive MIMO systems with MRT-based linear precoders.more » « less
-
null (Ed.)FPGAs are getting an increasing interest from public clouds and cloud research projects. They are particularly attractive because of their ability to serve as energy efficient and customizable hardware accelerators. Commercial clouds have however highlighted the lack of multi-tenancy support, which does not permit hardware consolidation as it is not possible to space-share FPGA resources between multiple tenants. In this paper, we propose an architecture that divides the FPGA into logically isolated regions that we call ” virtual regions ” (VR). The VRs are immersed in a NoC interconnect allowing flexible communication, fast data movement, and low hardware footprint. The proposed architecture enables multitenancy as VRs can be allocated to different tenants at runtime.more » « less
-
The 2022 settlement between Meta and the U.S. Department of Justice to resolve allegations of discriminatory advertising resulted is a first-of-its-kind change to Meta's ad delivery system aimed to address algorithmic discrimination in its housing ad delivery. In this work, we explore direct and indirect effects of both the settlement's choice of terms and the Variance Reduction System (VRS) implemented by Meta on the actual reduction in discrimination. \newline We first show that the settlement terms allow for an implementation that does not meaningfully improve access to opportunities for individuals. The settlement measures impact of ad delivery in terms of impressions, instead of unique individuals reached by an ad; it allows the platform to level down access, reducing disparities by decreasing the overall access to opportunities; and it allows the platform to selectively apply VRS to only small advertisers. \newline We then conduct experiments to evaluate VRS with real-world ads, and show that while VRS does reduce variance, it also raises advertiser costs (measured per-individuals-reached), therefore decreasing user exposure to opportunity ads for a given ad budget. VRS thus \emph{passes the cost of decreasing variance to advertisers}. \newline Finally, we explore an alternative approach to achieve the settlement goals, that is significantly more intuitive and transparent than VRS. We show our approach outperforms VRS by both increasing ad exposure for users from \emph{all} groups and reducing cost to advertisers, thus demonstrating that the increase in cost to advertisers when implementing the settlement is not inevitable. \newline Our methodologies use a black-box approach that relies on capabilities available to any regular advertiser, rather than on privileged access to data, allowing others to reproduce or extend our work.more » « less
-
null (Ed.)Accurate selectivity estimation for string predicates is a long-standing research challenge in databases. Supporting pattern matching on strings (such as prefix, substring, and suffix) makes this problem much more challenging, thereby necessitating a dedicated study. Traditional approaches often build pruned summary data structures such as tries followed by selectivity estimation using statistical correlations. However, this produces insufficiently accurate cardinality estimates resulting in the selection of sub-optimal plans by the query optimizer. Recently proposed deep learning based approaches leverage techniques from natural language processing such as embeddings to encode the strings and use it to train a model. While this is an improvement over traditional approaches, there is a large scope for improvement. We propose Astrid, a framework for string selectivity estimation that synthesizes ideas from traditional and deep learning based approaches. We make two complementary contributions. First, we propose an embedding algorithm that is query-type (prefix, substring, and suffix) and selectivity aware. Consider three strings 'ab', 'abc' and 'abd' whose prefix frequencies are 1000, 800 and 100 respectively. Our approach would ensure that the embedding for 'ab' is closer to 'abc' than 'abd'. Second, we describe how neural language models could be used for selectivity estimation. While they work well for prefix queries, their performance for substring queries is sub-optimal. We modify the objective function of the neural language model so that it could be used for estimating selectivities of pattern matching queries. We also propose a novel and efficient algorithm for optimizing the new objective function. We conduct extensive experiments over benchmark datasets and show that our proposed approaches achieve state-of-the-art results.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/GLOBECOM52923.2024.10901212
