The dataset is a structured image dataset designed to facilitate spatial localization, pattern recognition, and character classification research. It contains high-resolution images of 53 distinct alphabet characters, each systematically placed within a standardized 5×5 grid layout.
This is a voiceprint dataset with speaker's normal voice and special voice.
We recruited user test participants by snowballing. We directly invited 34 participants, all of them are family members, friends and classmates of the authors, ranging in age from 16 to 55, with similar technical backgrounds. Next, the involved participants further invited their relatives and friends to join, then 21 additional participants joined our user study. Finally, 56 people participated in our user study.
This is a voiceprint dataset with speaker's normal voice and special voice.
We recruited user test participants by snowballing. We directly invited 34 participants, all of them are family members, friends and classmates of the authors, ranging in age from 16 to 55, with similar technical backgrounds. Next, the involved participants further invited their relatives and friends to join, then 21 additional participants joined our user study. Finally, 56 people participated in our user study.
Smart Home Automation (SHA) has significantly improved homes’ convenience, comfort, security, and safety. It has gained widespread use due to its intelligent monitoring and quick response capabilities. The current state of SHA enables effective monitoring and motion detection. However, false notifications remain a significant challenge, as they can cause unnecessary alarms in intrusion detection systems. To address this, we propose an intelligent model for a smart home security system that uses computer vision techniques to detect trespasser movement near the boundary wall.
This dataset used in the research paper "JamShield: A Machine Learning Detection System for Over-the-Air Jamming Attacks." The research was conducted by Ioannis Panitsas, Yagmur Yigit, Leandros Tassiulas, Leandros Maglaras, and Berk Canberk from Yale University and Edinburgh Napier University.
For any inquiries, please contact Ioannis Panitsas at ioannis.panitsas@yale.edu.
To provide a standardized approach for testing and benchmarking secure evaluation of transformer-based models, we developed the iDASH24 Homomorphic Encryption track dataset. This dataset is centered on protein sequence classification as the benchmark task. It includes a neural network model with a transformer architecture and a sample dataset, both used to build and evaluate secure evaluation strategies.
"Recent advancements in deep learning and generative models have significantly enhanced text-to-image (T2I) synthesis, allowing for the creation of highly realistic images based on textual inputs. While this progress has expanded the creative and practical applications of AI, it also presents new challenges in distinguishing between authentic and AI-generated images. This challenge raises serious concerns in areas such as security, privacy, and digital forensics.
In the evolving landscape of 5G network, network slicing has been considered as a key technology for the realization of multiple virtual networks running on a shared physical infrastructure, each designed to fulfill a specific service or application. However, with such networks, the dynamic and real-time allocation of these resources remains a prime concern, particularly with respect to highly variable conditions of traffic.
This data reflects the prevalence and adoption of smart devices. The experimental setup to generate the IDSIoT2024 dataset is based on an IoT network configuration consisting of seven smart devices, each contributing to a diverse representation of IoT devices. These include a smartwatch, smartphone, surveillance camera, smart vacuum and mop robot, laptop, smart TV, and smart light. Among these, the laptop serves a dual purpose within the network.
The security of systems with limited resources is essential for deployment and cannot be compromised by other performance metrics such as throughput. Physically Unclonable Functions (PUFs) present a promising, cost-effective solution for various security applications, including IC counterfeiting and lightweight authentication. PUFs, as security blocks, exploit physical variations to extract intrinsic responses based on applied challenges, with Challenge-Response Pairs (CRPs) uniquely defining each device.
