Center for Machine Learning and Intelligent Systems
About  Citation Policy  Donate a Data Set  Contact


Repository Web            Google
View ALL Data Sets

Unmanned Aerial Vehicle (UAV) Intrusion Detection Data Set
Download: Data Folder, Data Set Description

Abstract: For UAV identification, each input is an encrypted WiFi traffic record while the output is whether the current traffic is from a UAV or not. Meta-info on attribute relationship is also provided.

Data Set Characteristics:  

Multivariate

Number of Instances:

17256

Area:

Computer

Attribute Characteristics:

Real

Number of Attributes:

55

Date Donated

2020-04-12

Associated Tasks:

Classification

Missing Values?

N/A

Number of Web Hits:

1528


Source:

Liang Zhao, George Mason University (lzhao9 '@' gmu.edu)

A. Alipour-Fanid, M. Dabaghchian, N. Wang, P. Wang, L. Zhao and K. Zeng, 'Machine Learning-Based Delay-Aware UAV Detection and Operation Mode Identification Over Encrypted Wi-Fi Traffic,' in IEEE Transactions on Information Forensics and Security, vol. 15, pp. 2346-2360, 2020.


Data Set Information:

Beyond traditional classification task, this dataset also contains other meta-information that help enable additional machine learning tasks. For example, this dataset contains the computational generation time for each statistical attributes, which is recorded in the diagonal values of the matrix D. It also contains the computational dependency among different attributes, which is denoted by the incidence matrix H. For example, the computation of standard deviation contains the computation of mean. Detailed information on D and H are as follows:
D: k× 1. The generation runtime for each feature.
H: k'×k. The incident matrix of the feature computational hypergraph (see the above paper for details). k' is the number of feature computational components and k is the numbe of features.
More information is included in the source paper.


Attribute Information:

The raw inputs are the radio frequency time series in two directions: uplink_flow and downlink_flow. Attributes are processed from the raw input, the list of attributes are:
1. uplink_size_mean
2. uplink_size_median
3. uplink_size_MAD
4. uplink_size_STD
5. uplink_size_Skewness
6. uplink_size_Kurtosis
7. uplink_size_MAX
8. uplink_size_MIN
9. uplink_size_MeanSquare
10. downlink_size_mean
11. downlink_size_median
12. downlink_size_MAD
13. downlink_size_STD
14. downlink_size_Skewness
15. downlink_size_Kurtosis
16. downlink_size_MAX
17. downlink_size_MIN
18. downlink_size_MeanSquare
19. both_links_size_mean
20. both_links_size_median
21. both_links_size_MAD
22. both_links_size_STD
23. both_links_size_Skewness
24. both_links_size_Kurtosis
25. both_links_size_MAX
26. both_links_size_MIN
27. both_links_size_MeanSquare
28. uplink_interval_mean
29. uplink_interval_median
30. uplink_interval_MAD
31. uplink_interval_STD
32. uplink_interval_Skewness
33. uplink_interval_Kurtosis
34. uplink_interval_MAX
35. uplink_interval_MIN
36. uplink_interval_MeanSquare
37. downlink_interval_mean
38. downlink_interval_median
39. downlink_interval_MAD
40. downlink_interval_STD
41. downlink_interval_Skewness
42. downlink_interval_Kurtosis
43. downlink_interval_MAX
44. downlink_interval_MIN
45. downlink_interval_MeanSquare
46. both_links_interval_mean
47. both_links_interval_median
48. both_links_interval_MAD
49. both_links_interval_STD
50. both_links_interval_Skewness
51. both_links_interval_Kurtosis
52. both_links_interval_MAX
53. both_links_interval_MIN
54. both_links_interval_MeanSquare
55. label


Relevant Papers:

Liang Zhao, Amir Alipour-Fanid, Martin Slawski and Kai Zeng. Prediction-time Efficient Classification Using Feature Computational Dependencies. in Proceedings of the 24st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2018), research track (acceptance rate: 18.4%), London, United Kingdom, Aug 2018, Pages 2787-2796.

Qingzhe Li, Amir A. Fanid, Martin Slawski, Yanfang Ye, Lingfei Wu, Kai Zeng, and Liang Zhao. Large-scale Cost-aware Classification Using Feature Computational Dependency Graph. IEEE Transactions on Knowledge and Data Engineering (TKDE), (impact factor: 3.857), to appear.



Citation Request:

To use these datasets, please cite the paper:

Liang Zhao, Amir Alipour-Fanid, Martin Slawski and Kai Zeng. Prediction-time Efficient Classification Using Feature Computational Dependencies. in Proceedings of the 24st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2018), research track (acceptance rate: 18.4%), London, United Kingdom, Aug 2018, Pages 2787-2796Â .

@inproceedings{Zhao:2018:[Web Link],
author = {Zhao, Liang and Alipour-Fanid, Amir and Slawski, Martin and Zeng, Kai},
title = {Prediction-time Efficient Classification Using Feature Computational Dependencies},
booktitle = {Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining},
year = {2018},
location = {London, United Kingdom},
pages = {2787--2796},
doi = {10.1145/3219819.3220117},
publisher = {ACM},
}


Supported By:

 In Collaboration With:

About  ||  Citation Policy  ||  Donation Policy  ||  Contact  ||  CML