Ningning Wang

Ningning Wang

Auto-generated profile, based on publicly available information

Ningning Wang

Florida International University, Miami, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 February 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
NWNingning Wang
Ningning Wang
SLSilong Li
Silong Li
TYTerry Ye
Terry Ye
Gas sensor array (GSA) data is a sequential series of values that represents the temporal conditions of the existence/absence/mixture of gases, and exhibits similarities to the textual stream of natural languages that represents semantic information. We speculate and subsequently prove that there also exist self-attention mechanisms in GSA data that can be exploited for gas classification and recognition. We first convert GSA data into a one-dimensional token series (called WORDs in this work) through sampling and quantization of the sensor values, then use an enhanced LSTM revision network, called LSTM-attention, to extract the self-attention mechanism in the GSA data. We demonstrate that LSTM-attention achieves a much better performance (99.6%) than CNN-based networks as well as other GSA data process techniques on UCI dynamic gases dataset. We also find out that the self-attention mechanism varies with different sampling and quantization levels during data acquisition.

4 December 2024
Verified
Conference Paper
Open access
TZTianya Zhao
Tianya Zhao
NWNingning Wang
Ningning Wang
SMShiwen Mao
Shiwen Mao
XWXuyu Wang
Xuyu Wang
In this paper, we propose a novel approach to cross-domain unmanned aerial vehicle (UAV) authentication using radio frequency (RF) fingerprinting based on prototypical networks (PTNs). UAVs present a unique challenge for RF fingerprinting due to their hovering motion, which creates more diverse signal domains compared to other RF devices like Wi-Fi. This results in a severe domain shift problem, where well-trained models struggle to generalize to unseen domains. To address this issue without incurring significant costs in data collection and model retraining, we employ PTNs, a few-shot learning paradigm that enhances cross-domain performance and system viability. We further improve our method's effectiveness by incorporating fine-tuning with data augmentation, maintaining system viability while improving performance. Comprehensive experimental results demonstrate that our approach significantly mitigates domain shift, achieving up to a 20% improvement in cross-domain accuracy for UAV fingerprinting.

6 May 2025
Verified
Conference Paper
Open access
TZTianya Zhao
Tianya Zhao
NWNingning Wang
Ningning Wang
XWXuyu Wang
Xuyu Wang
Deep learning has revolutionized the use of inertial measurement unit (IMU) sensors in mobile applications, such as human activity recognition. Building on the success of pre-trained models across various domains, recent studies have increasingly adopted self-supervised learning (SSL) for a range of sensing tasks. While these SSL approaches improve generalization and reduce labeling requirements, their privacy implications have received limited attention. This paper addresses this gap by examining IMU data privacy during pre-training through membership inference. Our work serves two important purposes: First, it enables data owners to verify if their data was used without permission in encoder pre-training. Second, it demonstrates how adversaries might compromise sensitive human sensing data used in pre-training. To enhance the practicality of membership inference on unlabeled IMU sensing data across different SSL algorithms, we introduce an activity labeling module and a novel perturbation strategy to exploit encoder overfitting characteristics on training data. When an encoder over-fits, it memorizes training data rather than learning generalizable patterns. Therefore, when comparing the original data to the perturbed version, the encoder generates more distinct feature vectors for samples from its training set than for samples it has never seen before. We evaluate our membership inference methods on two mainstream SSL methods across multiple datasets, demonstrating that our method can achieve relatively high precision and recall at low false positive rates.