Security
In deep learning, images are utilized due to their rich information content, spatial hierarchies, and translation invariance, rendering them ideal for tasks such as object recognition and classification. The classification of malware using images is an important field for deep learning, especially in cybersecurity. Within this context, the Classified Advanced Persistent Threat Dataset is a thorough collection that has been carefully selected to further this field's study and innovation.
- Categories:
1593 Views
Microsoft contains a productive tool known as MS Office but the inclusion of VBA Macros inside the MS Office for automation purposes makes it a way for attackers to perform malicious activities. To get an up-to-date dataset, the research regarding VBA macros is still working to find efficient ways to detect it. To perform analysis, the dataset is required which is publically harder to find. To overcome this issue, a dataset is created from VirusTotal, VirusShare, Zenodo, Malware Bazaar, Github and InQuest Labs.
- Categories:
1070 Views
The WPT dataset was specially created for "Web Page Tampering Detection Based on Dynamic Temporal Graph Pre-training" and encompasses over 200,000 regular web pages from 75 websites across the finance, healthcare, and education sectors, in addition to 1,541 tampered examples sourced from zone-h.org. This dataset organizes web pages as nodes and their links as edges within a discrete dynamic graph structure, capturing snapshots at various moments in time. Each node integrates structural, textual, and statistical features into a robust 148-dimensional feature vector for every page.
- Categories:
61 Views
The sudden shift from physical office location to a fully remote or hybrid work model accelerated by the COVID-19 pandemic is a phenomenon that changed how organizations traditionally operated and thereby introduced new vulnerabilities and consequently changed the cyber threat landscape. This has led organizations around the globe to seek new approaches to protect their enterprise network. One such approach is the adoption of the Zero Trust security approach due to its many advantages over the traditional/perimeter security approach.
- Categories:
484 Views
A Wormhole attack in a dataset, where certain nodes (wormhole nodes) create an illusion of having a shorter path in network communications to attract traffic, the dataset will reflect network traffic patterns altered by these deceptive links. Here’s the structure for 95,000 records:
- Categories:
317 Views
a Sinkhole attack in a dataset, we'll generate data that typically reflects network traffic and interactions, where some nodes act as sinkholes by attracting all or most of the traffic due to malicious intent. Here's how I'll structure the dataset for 80,000 records:
- Categories:
299 Views
a dataset with 50,000 records simulating a Sybil attack scenario. Here's the plan for each record in the dataset:
- Categories:
339 Views
An IEEE 802.15.4 backscatter communication dataset for Radio Frequency (RF) fingerprinting purposes.
It includes I/Q samples of transmitted frames from six carrier emitters, including two USRP B210 devices (labeled as c#) and four CC2538 chips (labeled as cc#), alongside ten backscatter tags (identified as tag#). The carrier emitters generate an unmodulated carrier signal, while the backscatter tags employ QPSK modulation within the 2.4 GHz frequency band, adhering to the IEEE 802.15.4 protocol standards.
- Categories:
422 Views
X-CANIDS Dataset (In-Vehicle Signal Dataset)
In March 2024, one of our recent research "X-CANIDS: Signal-Aware Explainable Intrusion Detection System for Controller Area Network-Based In-Vehicle Network" was published in IEEE Transactions on Vehicular Technology. Here we publish the dataset used in the article. We hope our dataset facilitates further research using deserialized signals as well as raw CAN messages.
Real-world data collection. Our benign driving dataset is unique in that it has been collected from real-world environments.
- Categories:
1510 Views
This dataset comprises audio recordings of ultra-high-frequency ambient noise stored in the lossless waveform format (WAW). The recordings were sampled at a frequency sample rate of 2.048 MHz and then provided at a downsampled audio rate of 48 kHz for compatibility and practical usage. The total length of the dataset is 01:30:29, consisting of approximately 260 million data points. (2024-03-30)
- Categories:
22 Views