Scribd
Upload
14 views2 pages

Reser 12

The document outlines various metadata types related to network flows, including flow-based, packet-based, flag indicators, header metrics, and labels for classifying network traffic. It also lists multiple research papers focused on Android malware detection using various techniques such as deep learning, static analysis, and hybrid models. These studies aim to enhance the effectiveness and efficiency of identifying and classifying Android malware.

Uploaded by

zfazza4
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
14 views2 pages

Reser 12

The document outlines various metadata types related to network flows, including flow-based, packet-based, flag indicators, header metrics, and labels for classifying network traffic. It also lists multiple research papers focused on Android malware detection using various techniques such as deep learning, static analysis, and hybrid models. These studies aim to enhance the effectiveness and efficiency of identifying and classifying Android malware.

Uploaded by

zfazza4
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Flow-Based Metadata

 Flow ID: Unique identifier for the flow (a combination of source and destination IP, port, and
protocol).
 Source IP: IP address of the source host.
 Source Port: Port number on the source host.
 Destination IP: IP address of the destination host.
 Destination Port: Port number on the destination host.
 Protocol: Communication protocol used (e.g., TCP, UDP, ICMP).
 Timestamp: Start time of the flow.
 Flow Duration: Total time duration of the flow (in microseconds).

Packet-Based Metadata
 Total Fwd Packets: Total number of packets sent from the source to the destination.
 Total Backward Packets: Total number of packets sent from the destination to the source.
 Total Length of Fwd Packets: Total size (in bytes) of all forward packets.
 Total Length of Bwd Packets: Total size (in bytes) of all backward packets.
 Fwd Packet Length Max/Min/Mean/Std: Statistics for forward packet lengths (maximum,
minimum, average, standard deviation).
 Bwd Packet Length Max/Min/Mean/Std: Statistics for backward packet lengths (maximum,
minimum, average, standard deviation).

Flag Indicators
 Fwd PSH Flags: Count of push (PSH) flags in forward direction.
 Bwd PSH Flags: Count of push (PSH) flags in backward direction.
 Fwd URG Flags: Count of urgent (URG) flags in forward direction.
 Bwd URG Flags: Count of urgent (URG) flags in backward direction.

Header Metrics
 Fwd Header Length: Total length of the forward headers (in bytes).
 Bwd Header Length: Total length of the backward headers (in bytes).

Label
 Label: Indicates whether the flow is benign or belongs to a specific attack/malicious category.
Used in supervised learning scenarios for network security analysis.

TASK 2

1- Hybrid-Based Malware Analysis for Effective and Efficiency


Android Malware Detection

2- Abstract HTML Static Analysis of Android Malware Detection using Deep Learning

3- Detecting Android Malware Based on Dynamic Feature Sequence and Attention Mechanism
4- Opcode n-gram based Malware Classification in Android
5- Droid-NNet: Deep Learning Neural Network for Android Malware Detection
6- Android Malware Detection using Deep Learning
7- COVID-Themed Android Malware Analysis and Detection Framework Based on Permissions
8- A Survey on Android Malware and their Detection Techniques
9- Feature Selection and Evaluation of Permission-based Android Malware Detection
10- Android Malware Detection and its Security
11- A state-of-the-art Analysis of Android Malware Detection Methods
12- Detect Malware in Android Firmware Based on Distributed Network Environment
13- Poster: Android Malware Detection using Hybrid Features and Machine Learning
14- Android Malware A Oversight on Malware Detection Using Machine Learning
15- Android Malware Detection based on Feature-pair Bonding: A Hybrid Detection Model

You might also like