The two datasets here record behavioural activity for malicious and benign executable files capable of running on a Windows 7 operating system.
Dataset 1:
filename = "data_1.csv"
594 benign samples
595 malicious samples
Up to 305 seconds (5:05 min) execution per file
The data was collected in a VirtualBox[1] virtual machine using Cuckoo Sandbox[2] with a custom package written in the Java library, Sigar[3] to collect the machine activity data.
The virtual machine used 2GB RAM, 25 GB storage, and a single CPU core running 64-bit Windows 7.
Dataset 2:
filename = "data_2.csv"
2345 benign samples
2286 malicious samples
Up to 20 seconds execution per file
The data was collected in a VirtualBox[1] virtual machine using Cuckoo Sandbox[2] with a custom package written in the python library, Psutil[4] to collect the machine activity data.
The virtual machine used 8GB RAM, 25 GB storage, and a single CPU core running 64-bit Windows 7.
Columns
sample_id: an identifier value for the samples (categorical)
vector: time in seconds since start of file execution (numeric)
malware: class label 0=benign, 1=malicious (categorical)
cpu_sysem: percentage of cpu being used to run programs in system kernel (numeric)
cpu_user: percentage of cpu being used to run programs in user space (numeric)
memory: bytes currently being used in memory (numeric)
swap: bytes currently being used in swap memory (numeric)
total_pro: total number of processes running (numeric)
max_pid: maximum process id held by a process (numeric)
rx_bytes: number of bytes being received (numeric)
tx_bytes: number of bytes being sent (numeric)
rx_packets: number of packets being received (numeric)
tx_packets: number of packets being sent (numeric)
test_set: True=sample belongs to test set, False=sample belongs to training set
Dataset 2 only:
family: malware type - value missing if unknown or benign (categorical)
variant: malware variant - value missing unknown or benign (categorical)
test-set: file was first seen before October (categorical)
Research results based upon these data are published at http://doi.org/10.1016/j.cose.2018.05.010
Funding
Deep Learning Methods for the Analysis of Cyber Behaviour and Detection of Cyber Risk (2016-10-01 - 2020-09-30); Rhode, Matilda. Funder: Airbus Operations Ltd, Engineering and Physical Sciences Research Council