FUPE HELP- Read me

All the codes are zipped as Zip format here

Codes (JISA, Fog-Security and VM Placement)

F. Aghili, H. Mala, Ch. Schindelhauer, M. Shojafar, R. Tafazolli, 'Closed-Loop and Open-Loop Authentication Protocols for Blockchain-based IoT Systems
', Information Processing & Management, February 2021.

Codes (IEEE TGCN, Cloud paper)

IEEE TGCN 2021

AFED-EF-Introduction of the paper and experiment explanations

A. Shahidinejad, M. Ghobaei-Arani, A. Souri, M. Shojafar, S. Kumari, "Light-Edge: A Lightweight Authentication Protocol for IoT Devices in an Edge-Cloud Environment", IEEE Consumer Electronics Magazine, pp. 1-6, January 2021.
DOI: https://doi.org/10.1109/MCE.2021.3053543

README.txt

Help file to run the project written in Python 2.7 and 3.0.

Dr. Rahim Taheri did this implementation. 
Dr. Rahim Taheri, Dr. Mohammad Shojafar and Dr. Zahra Pooranian helped on idea brainstorming and documentation. 
Prof. Reza Javidan, Prof. Ali Miri and Prof. M. Conti helped in English correction and leading the team.

If you need any help on the code, feel free to drop a message to

Dr. Mohammad Shojafar <mohammad.shojafar@gmail.com> or <m.shojafar@ieee.org> or
Dr. Rahim Taheri <taheri.rahim@gmail.com> 

Step of the running project:

Label_Flipping_Paper_with_Feature_Selection(LSD_CSD_KDD).py is for label flipping code with feature selection method on LSD CSD and KDD

Label_Flipping_Paper_without_Feature_Selection(LSD_CSD_KDD).py is for label flipping code without feature selection method on LSD CSD and KDD

The comparisons are embedded in the code.

We used three datasets which can be obtained through the links on the paper. 

Note: you need to preprocess and clean the dataset before implementation. 


I will be glad to cite our paper with the following details in your research papers:

R. Taheri, R. Javidan, M. Shojafar, Z. Pooranian, A. Miri, M. Conti, "On Defending Against Label Flipping Attacks on Malware Detection Systems", Springer, Neural Computing and Applications (NCAA), Vol. 32, pp. 14781–14800, July 2020.

DOI: https://doi.org/10.1007/s00521-020-04831-9

README.txt

Help file to run the project written in Python 2.7 and 3.0.

Dr. Rahim Taheri did this implementation. 
Dr. Rahim Taheri, Dr. Mohammad Shojafar and Dr. Zahra Pooranian helped on idea brainstorming and documentation. 
Prof. Reza Javidan, Prof. Ali Miri and Prof. M. Conti helped in English correction and leading the team.

If you need any help on the code, feel free to drop a message to

Dr. Mohammad Shojafar <mohammad.shojafar@gmail.com> or <m.shojafar@ieee.org> or
Dr. Rahim Taheri <taheri.rahim@gmail.com> 

Step of the running project:

Label_Flipping_Paper_with_Feature_Selection(LSD_CSD_KDD).py is for label flipping code with feature selection method on LSD CSD and KDD

Label_Flipping_Paper_without_Feature_Selection(LSD_CSD_KDD).py is for label flipping code without feature selection method on LSD CSD and KDD

The comparisons are embedded in the code.

We used three datasets which can be obtained through the links on the paper. 

Note: you need to preprocess and clean the dataset before implementation. 


I will be glad to cite our paper with the following details in your research papers:

R. Taheri, R. Javidan, M. Shojafar, Z. Pooranian, A. Miri, M. Conti, "On Defending Against Label Flipping Attacks on Malware Detection Systems", Springer, Neural Computing and Applications (NCAA), Vol. 32, pp. 14781–14800, July 2020.

DOI: https://doi.org/10.1007/s00521-020-04831-9

README.txt

Help file to run the project written in Python 2.7 and 3.0.

Dr. Rahim Taheri did this implementation. 
Dr. Rahim Taheri, Dr. Mohammad Shojafar and Dr. Meysam Ghahramani helped on idea brainstorming and documentation. 
Reza Javidan, Zahra Pooranian and Mauro Conti helped in English correction and leading the team.

If you need any help on the code, feel free to drop a message to

Dr. Mohammad Shojafar <mohammad.shojafar@gmail.com> or <m.shojafar@ieee.org> or
Dr. Rahim Taheri <taheri.rahim@gmail.com> 

Step of the running project:

Label_Flipping_Paper_with_Feature_Selection.py is for label flipping code with feature selection method

Label_Flipping_Paper_without_Feature_Selection.py is for label flipping code without feature selection method

The comparisons are embedded in the code.

We used three datasets which can be obtained through the links on the paper. 

Note: you need to preprocess and clean the dataset before implementation. 


I will be glad to cite our paper with the following details in your research papers:

R. Taheri, M. Ghahramani, R. Javidan, M. Shojafar, Z. Pooranian, M. Conti, "Similarity-based Android Malware Detection Using Hamming Distance of Static Binary Features", Elsevier, Future Generation Computer Systems, (FGCS), Vol. 105, pp. 230-247, April 2020. 

DOI: https://doi.org/10.1016/j.future.2019.11.034

README.txt

Help file to run the project written in Matlab.

Dr. Mohammad Mahdi Tajiki did this implementation. 
Dr. Mohammad Shojafar, Dr. Mohammad Mahdi Tajiki helped on idea brainstorming and documentation. 
S. Salsano, L. Chiaraviglio, B. Akbari helped in English correction and leading the team.

If you need any help on the code, feel free to drop a message to

Dr. Mohammad Shojafar <mohammad.shojafar@gmail.com> or <m.shojafar@ieee.org> or
Dr. Mohammad Mahdi Tajiki <mohammad59mt@gmail.com> 

Step of the running project:

How to run the code:

The code is done using CVX solver on MATLAB.

First, you are requested to download and install CVX solver from http://cvxr.com/cvx/doc/solver.html

Then, you can easily access model file for all the scenarios of the published paper in Wiley CPE in the ‘Simulation’ folder.

1. ’CreateTopology.m’ is used to establish the topology of the network, e.g., Abilene topology
2. ‘CreateVMs.m’ is used to establish VMs riding on each server/node of the designed topology
3. ‘SolverForONR.m’ and ‘SFC_ONR.m’ are the solver code (CVX) for ONR algorithm for without SFC and with SFC, respectively.  
4. ‘HNR-RR.m’ is used to address the relaxation of HNR algorithm. 
5. The rest m files are used to plot the results and make analytics of the results.

I will be glad to cite our paper with the following details in your research papers:
Wiley CPE:

M.M. Tajiki, M. Shojafar, S. Salsano, M. Shojafar, L. Chiaraviglio, B. Akbari, "Energy-efficient Path Allocation Heuristic for Service Function Chaining", The 21st IEEE Conference on Innovations in Clouds, Internet and Networks, (ICIN 2018), Paris, France, pp. 1-8, 2018. DOI: https://doi.org/10.1109/ICIN.2018.8401618


The papers are supported and fully funded by H2020 EU project named:

SUPERFLUIDITY

Project Link: http://superfluidity.eu/

(grant agreement No. 671566)

README.txt

Help file to run the project written in Matlab.

Dr. Mohammad Mahdi Tajiki did this implementation. 
Dr. Mohammad Shojafar, Dr. Mohammad Mahdi Tajiki helped on idea brainstorming and documentation. 
S. Salsano, L. Chiaraviglio, B. Akbari helped in English correction and leading the team.

If you need any help on the code, feel free to drop a message to

Dr. Mohammad Shojafar <mohammad.shojafar@gmail.com> or <m.shojafar@ieee.org> or
Dr. Mohammad Mahdi Tajiki <mohammad59mt@gmail.com> 

Step of the running project:

How to run the code:

The code is done using CVX solver on MATLAB.

First, you are requested to download and install CVX solver from http://cvxr.com/cvx/doc/solver.html

Then, you can easily access model file for all the scenarios of the published paper in Wiley CPE in the ‘Simulation’ folder.

1. ’CreateTopology.m’ is used to establish the topology of the network, e.g., Abilene topology
2. ‘CreateVMs.m’ is used to establish VMs riding on each server/node of the designed topology
3. ‘SolverForONR.m’ and ‘SFC_ONR.m’ are the solver code (CVX) for ONR algorithm for without SFC and with SFC, respectively.  
4. ‘HNR-RR.m’ is used to address the relaxation of HNR algorithm. 
5. The rest m files are used to plot the results and make analytics of the results.

I will be glad to cite our paper with the following details in your research papers:
Wiley CPE:

M.M. Tajiki, M. Shojafar, S. Salsano, M. Shojafar, L. Chiaraviglio, B. Akbari, "Energy-efficient Path Allocation Heuristic for Service Function Chaining", The 21st IEEE Conference on Innovations in Clouds, Internet and Networks, (ICIN 2018), Paris, France, pp. 1-8, 2018. DOI: https://doi.org/10.1109/ICIN.2018.8401618


The papers are supported and fully funded by H2020 EU project named:

SUPERFLUIDITY

Project Link: http://superfluidity.eu/

(grant agreement No. 671566)

README.txt

Help file to run the project written in Matlab.

Dr. Rahim Taheri and Dr. Mohammad Shojafar did this implementation. 
Dr. Mohammad Shojafar, Dr. Rahim Taheri, Dr. Zahra Pooranian helped on idea brainstorming and documentation. 
Dr. Reza Javidan, Prof. Ali Miri, Prof. Yaser Jararweh helped in English correction and leading the team.

Contact: Dr. Mohammad Shojafar / Dr. Rahim Taheri
Email: m.shojafar@surrey.ac.uk; m.shojafar@ieee.org/ r.taheri@sutech.ac.ir; tahery.rahim@gmail.com 

Step of the running project:

1.	Open this project in your Matlab. the NLS-KDD 10% dataset is preprocessed and saved in ‘KDD.mat’
2.	You can run ‘abc.m’ to run abc algorithm.
3.	You can run ‘abc2.m’ to run abc2 algorithm.
4.	You can run ‘de.m’ to run deferential evaluation algorithm.
5.	You can run ‘pso.m’ to particle swarm optimization algorithm.
6.	You can run ‘hs.m’ to run hs algorithm.
7.	Since we use two indexes for the analyzing of the cost of each method, you can set line 7 of each algorithm code (default, ``Method = 'DB';	% DB or CS``) to DB representing DBindex.m and CS representing CSindex.m
8.	You can uncomment the figure instruction to see the result of each algorithm result at the end of each algorithm.

If you use this code, we will be happy to cite this paper (original published work):

M. Shojafar, R. Taheri, Z. Pooranian, R. Javidan, A. Miri, Y. Jararweh, "Automatic Clustering of Attacks in Intrusion Detection Systems", The 16th ACS/IEEE International Conference on Computer Systems and Applications, (ACS/IEEE 2019), Abu Dhabi, UAE, 3-7 November 2019.