1. INTRODUCTION:

Cyber security is the process of protecting network, technology, system from digital attacks which prevent accessing, changing destroying information. We always aim to limit attacker access to and movement within a network by partition the network into multiple segments or enclaves and restricting communications between enclaves and between enclaves and the Internet. The network requires dividing by the use of ﬁrewalls, network egress and ingress ﬁlters, application-level ﬁlters, and/or physical (hardware) infrastructure. Current needs to protect computer networks from cyber attacks, cybercrime (CC) and cyber terrorism (CT). As always in the history of the world, when new technology comes and used, it can be used for either good or immoral purposes. The same happens with the quick evolution of the communication networks and software applications which are now often the target of so called CC and cyber attacks. It is very difficult for large organizations like big industrial companies, banks; public administration to counter and eliminate cyber attacks, the same challenge applies to smaller organizations (e.g. SMEs) or citizens.

The general domain view on the security chain is as analyze and understand the context and situation; look for vulnerabilities; analyze threats and manage risks; observe the situation using sensors and monitoring capabilities (also humans); collect data; analyze data and, on the basis of the data processing and analysis; either detect danger and attacks, or decide that there are no attacks happening at a given moment. The last stage is the reaction and remediation, and of course, there are different reactions available depending on situation, capabilities and legal aspects. This chain of action is illustrated in Figure 1.

Figure 1 Cyber security chain of action

The rest of the paper review the working of nature inspired algorithm with its classification.

2. NATURE INSPIRED ALGORITHMS FOR CYBER SECURITY:

There are so many methods to analyze the collected data. The bio-inspired techniques can be used for network protection. There are two possible approaches based on detecting certain patterns in the observed data. The first approach is to learn patterns of cyber attacks and detect those patterns. The second approach is to learn the pattern of normal and safe state, and detect anomalies that do not ﬁt to the normal and typical patterns. Those two approaches apply not only to computer networks but also to security in general, e.g. in domains such as counter-terrorism, analysis of bank transactions, urban safety etc.

After reviewing the research some of the following features can be defines as:

1. Bio inspired features: As these algorithms are working same as the working mechanism of biological or ecological mechanism of natural algorithm. The Bio-inspired algorithm replicates the bio logical nature as much as possible to deal with the real-world problems.

2. Simplicity and emergence: strategy of the algorithm is often very simple, but their resulting effects are very remarkable, which reflects the standard of emergence.

3. Robustness: These algorithms have very well robustness property which accepts the change of environments, parameters, and tasks; namely, these algorithms have good applicability and flexibility.

4. Self-organization: As the nature works self-organization for any problem solution, these algorithms can improve the flexibility by self-learning or self-organization and realize the progress successfully.

The classification of Bio-inspired algorithms from the biometric medium are as follow as shown in the Figure 2.

Figure 2.The classifications of BIA.

3. THEORIES OVERVIEW:

There are some similarities in the property and application of each category with the same natural mechanism.

3.1. Inspired from Organism Behaviors:

Every living human being can live and care for itself in its own way, foraging of food, defending against natural enemy, and courtship displaying. Ant Colony Algorithm, Bee Colony Algorithm, Bacterial Foraging Algorithm, Fish Swarm Algorithm, and Shuffled Frog Leaping Algorithm are inspired from the foraging behaviors of organisms.

Monkey Climbing Algorithm:

Monkey Climbing Algorithm inspired by the actions of monkeys when they climb the trees to the best place for searching and to solve global optimization problems. There are three main processes in this algorithm, namely, climb process, watch-jump process, and somersault process.

(1) Climb process:

This process represents the local search of the algorithm. The monkeys climb from the initial positions and find the respective local optimum positions.

(2) Watch jump process:

This process represents the search process from local optimum to global optimum. The monkeys will look around when arriving at the local optimal positions. If s some better positions can be found, the monkeys will jump to these new positions; otherwise, they will stay where they are.

(3) Somersault process:

This process represents the search process for avoiding the local optimum. The monkeys will somersault to new positions at a certain probability and begin a new search.

The numerical computing processes of Monkey Climbing Algorithm are summarized as follows [20].

Step 1. Initialize the size of monkeys 𝑀 and the initial positions of all the monkeys. For the 𝑖th monkey, its position is denoted by 𝑥𝑖 = (𝑥 𝑖1, 𝑥 𝑖2,..., 𝑥 𝑖𝑛 ), where 𝑛 is the dimension of the solution.

Step 2. Optimize the positions of the monkeys by climbing. Set 𝑦 = (𝑦 1 ,𝑦 2 ,...,𝑦 𝑛 ), and

𝑦𝑖 =𝑥 𝑖𝑗 +𝑎⋅s g n(𝑓’ 𝑖𝑗 (𝑥 𝑖 )),

sgn(⋅) is a sign function; 𝑎>0 is the step length of the climb process; and 𝑓’𝑖𝑗 (𝑥 𝑖 ) is the pseudo gradient of the objective function 𝑓(⋅) at the position 𝑥𝑖, which is calculated by

Where Δ𝑥𝑖 = (Δ𝑥 𝑖1 , Δ𝑥 𝑖2, . . . , Δ𝑥 𝑖𝑛) and Δ𝑥𝑖𝑗 =𝑎 or −𝑎 with the same probability.

If position 𝑦 is feasible, update the position n of the monkey 𝑥𝑖 with 𝑦.

Step 3. Search for better places within the visual range of monkeys and update the ir positions. The detailed computing process is as follows:

Generate a number 𝑦𝑗 ⊆ (𝑥 𝑖𝑗 − 𝑏, 𝑥 𝑖𝑗 + 𝑏), where 𝑏 is a constant to denote the eye sight of the monkey. If 𝑓(𝑦) ≥

𝑓(𝑥 𝑖 ) and position 𝑦 is feasible, the 𝑖th monkey will move from positions 𝑥𝑖 to 𝑦, and go to Step2.

Step 4. Generate a random number 𝛼 ∈ [𝑐, 𝑑], where [𝑐, 𝑑] is the somersault interval.

Get a new 𝑦𝑗 =𝑥 𝑖𝑗 +𝛼(𝑝 𝑗 −𝑥 𝑖𝑗 ),

Where 𝑝 𝑗 = (1/𝑀) ∑ 𝑀 𝑖=1 𝑥 𝑖𝑗, 𝑗 = 1, 2, . . . , 𝑛.

If position 𝑦 is feasible, the n force the monkey to go to the new position 𝑦 and begin a search again.

Step5. If the results meet the end conditions, the search process is ended and output the position vector (the optimal solution). Otherwise, go to Step2.

Monkey Climbing Algorithm is the pseudo-gradient calculation of the objective function in the climb process, which only requires two measurements of the objective function regardless of the dimension of the real world problem. This advantage can reduce the cost of calculation and avoid the local minimum problem.

Ant Bee Colony (ABC) Algorithm: ABC is a new Swarm Intelligent algorithm inspired by the working behavior of honey bees [18]. This is based on three types of bees, employed bees, Onlooker bees and scout bees. Employed bees search food around the food source in their memory parallel they communicate information about food source with the Onlooker Bees. Higher quality food source is selected by the Onlooker bees, when the good food quality not improved with the current cycle then Scout bees are transformed by some employed bees, which dispose of food source and start new one.

ABC algorithm mathematically derives with the following equations [19].

Xij = Xj1+ rand(0,1)*(Xj2-Xj1)

Where Xi= (Xi1 , Xi2 ,.. Xid ) for dimension d i=(1,2,…Sn) and j=(1,2,..d)

Xj1= Lower bound Xj2 = Upper bound

Onlooker Bees evaluates the nectar information taken from all employed bees and choose a food source with the probabilities with the following equation:

The position of the i^th food source solution can be expressed

Particle swarm optimization:

PSO is a computational intelligence oriented, stochastic, population-based global optimization. It is inspired by the social behavior of bird flocking searching for food. PSO has been extensively applied to many engineering optimization areas due to its unique searching mechanism, simple concept, computational efficiency, and easy implementation. In PSO, the term “particles” refers to population members which are mass-less and volume-less (or with an arbitrarily small mass or volume) and are subject to velocities and accelerations towards a better mode of behavior. Each particle in the swarm represents a solution in a high-dimensional space with four vectors, its current position, best position found so far, the best position found by its neighborhood so far and its velocity and adjusts its position in the search space based on the best position reached by itself (pbest) and on the best position reached by its neighborhood (gbest) during the search process.

The required Steps in PSO algorithm is as follows:

1. Initialize the swarm by assigning a random position in the problem space to each particle.

2. Evaluate the fitness function for each particle.

3. For each individual particle, compare the particle‘s fitness value with its pbest . If the current value is better than the pbest value, then set this value as the pbest and the current particle‘s position, xi, as pi.

4. Identify the particle that has the best fitness value. The value of its fitness function is identified as guest and its position as pg.

5. Update the velocities and positions of all the particles using (1) and (2).

6. Repeat steps 2–5 until a stopping criterion is met (e.g., maximum number of iterations or a sufficiently good fitness value

Ant Colony Optimization:

It is a Meta heuristic inspired by the foraging behavior of ants in the wild, and moreover, the phenomena known as stigmergy, Stigmergy refers to the indirect communication amongst a self-organizing emergent system via individuals modifying their local environment. The most interesting aspect of the collaborative behavior of several ant species is their ability to find shortest paths between the ants' nest and the food sources by tracing pheromone trails Then, ants choose the path to follow by a probabilistic decision biased by the amount of pheromone: the stronger the pheromone trail, the higher its desirability. Because ants in turn deposit pheromone on the path they are following, this behavior results in a self-reinforcing process leading to the formation of paths marked by high pheromone concentration. By modeling and simulating ant foraging behavior, brood sorting, nest building and self- assembling, etc. algorithms can be developed that could be used for complex, combinatorial optimization problems.

Ant Solutions Construct: a solution building method in which the artificial ants go through nearby states of a problem according to a transition rule, iteratively building solutions.

Pheromone Update:

performs pheromone trail updates. This may involve updating the pheromone trails once complete solutions have been built, or updating after each iteration.

Deamon Actions:

Is an optional step in the algorithm which involves applying additional updates from a global perspective. This may include applying additional pheromone reinforcement to the best solution generated

3.2 Inspired from organism structure:

Nature creates all things, where life is the most incredible one. Each part of life composition can give us some inspirations. High parallelism; massive storage ability; low energy consumption. Inherent parallelism; distributed feature; non determinism Noise patience; learning without teacher; self- organization and identity are the advantages of it.

3.3 Inspired from evolution:

It is a High convergent reliability and convergent velocity with a double evolution structure; high search efficiency; with certain universality. Examples of these types of algorithm are Selfish Gene Algorithm, Invasive Weed Algorithm, and Culture Algorithm.

4. FUTURE SCOPE:

Bio inspired intelligent computing is a relatively novel inter disciplinary field of research, and there are many theoretical problems needed to be solved. The most important and widely studied theoretical problems are convergence problem, effectiveness problem, and evaluation standard problem. Because most of the BIAs are based on probability searching, it is difficult to rigorously prove the convergence and effectiveness of BIAs in mathematics. Currently, many theoretical research results are aiming at one specific algorithm to carry out the research work. One of the future works is to integrate some related algorithms to a common theory framework for the proof of convergence and effectiveness. In addition, the evaluation of BIAs should be conducted in a specific aspect for a specific task, such as the computing speed or the correctness of the solution, because it is difficult to find a BIA, which is suitable for all the problems.

5. CONCLUSION:

The fast development of technology has a many positive benefits with convenience advantages. In such scenario providing cyber security is a crucial task. The Natured inspired algorithm optimization techniques for the cyber security helps the hybrid method to construct and estimate the architectures, adapt to changing threat levels. The study about the system employs a hybrid approach that combines nature-inspired optimization methods with simulation modeling to construct and evaluate candidate architectures, intelligently search the space of possible architectures, and adapt to changing threat levels. We demonstrate the system via a case study on a representative network environment under an evolving cyber attack.

6. REFERENCES:

1. Neal Wagner, Cem ¸ S. ¸ Sahin, Jaime Pena, and William W. Streilein, "A Nature-inspired Decision System for Secure Cyber Network Architecture", MIT Lincoln Laboratory Lexington, MA, USA.

2. Fielder, “Decision support approaches for cyber security investment,” Decision Support Systems, vol. 86, pp. 13–23, 2016.

3. N. Wagner et al., “Towards automated cyber decision support: A case study on network segmentation for security,” in IEEE Symposium on Computational Intelligence for Cyber Security, December 2016.

4. Muhammad Mostafa Amir Faisal, Muhammad Ariful Islam Chowdhury, ”Bio Inspired Cyber Security Architecture for Smart Grid”, 2016.

5. Shikha Mehta Parul Agarwal, "Nature-Inspired Algorithms: State-of-Art, Problem and Prospects," International Journal of Computer Applications, vol. 100, no. 14, August 2014.

6. D. Dasgupta, (2006) “Computational Intelligence in Cyber Security”, IEEE International Conference on Computational Intelligence for Homeland Security and Personal Safety (CIHSPS 2006), pp. 2–3.

7. S. Poonia, A. Bhardwaj, G. S. Dangayach, (2011) “Cyber Crime: Practices and Policies for Its Prevention”, The First International Conference on Interdisciplinary Research and Development, Special No. of the International Journal of the Computer, the Internet and Management, Vol. 19, No.SP1.

8. Back, T. 1996: Evolutionary algorithms in theory and practice. Oxford University Press.

9. J.H. Holland, Genetic algorithms and the optimal allocation of trials, SIAM J. Comput. 2 (2) (1973) 88–105

10. Koza, John R. 1992. Genetic Programming: On the Programming of Computers by Means of Natural Selection. Cambridge, MA: The MIT Press.

11. Beyer, H.G. and Schwefel, H.P. 2002: Evolution strategies. Natural Computing 1,3–52.

12. Mukesh Gupta and Akansha Jain S. N. Tazi, "A Survey on application of nature inspired algorithms," International Journal of Computer Science Engineering and Information Technology Research (IJCSEITR), vol. 4, no. 4, pp. 33-40, August 2014.

13. Bonabeau, E., Dorigo, M. and Theraulaz, G.1999:Swarm intelligence. Oxford University Press

14. Kennedy, J.; Eberhart, R. (1995). "Particle Swarm Optimization". Proceedings of IEEE International Conference on Neural Networks. IV. pp. 1942– 1948.

15. Dorigo, M., Maniezzo, V., and Colorni, A. (1996). Ant System: Optimization by a colony of cooperating agents. IEEE Transactions on Systems, Man, and Cybernetics – Part B, 26, 29–41.

16. D. Karaboga, B. Basturk, A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm, Journal of Global Optimization 39 (2007) 459–471

17. X. Li, Z. Shao, J. Qian,Anoptimizing method base on autonomous animates: fish- swarm algorithm, Systems Engineering Theory and Practice 22 (2002) 32–38.

18. Shah_Hosseini, H. Shahid Beheshti Univ., Tehran Problem solving by intelligent water drops IEEE. Congress on Evolutionary Computation, 2007. CEC 2007.

19. Binitha S, S Siva Sathya, "A Survey of Bio inspired Optimization Algorithms", International Journal of Soft Computing and Engineering (IJSCE) ISSN: 2231-2307, Volume-2, Issue-2, May 2012.

20. Jianjun Ni, LiuyingWu, Xinnan Fan and Simon X. Yang, "Review Article Bioinspired Intelligent Algorithm and Its Applications for Mobile Robot Control: A Survey" Hindawi Publishing Corporation Computational Intelligence and Neuroscience Volume 2016, Article ID 3810903, 16 pages

21. Selma Dilek, Hüseyin Çakır and Mustafa Aydın, "Applications of Artificial Intelligence Techniques to Combating Cyber Crimes: A Review", International Journal of Artificial Intelligence and Applications (IJAIA), Vol. 6, No. 1, January 2015.

22. N. Wattanapongsakorn, S. Srakaew, E. Wonghirunsombat, C. Sribavonmongkol, T. Junhom, P. Jongsubsook, C. Charnsripinyo, (2012) “A Practical Network-based Intrusion Detection and Prevention System”, IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications, pp. 209 – 214.

23. A. S. A. Aziz, M. A. Salama, A. Hassanien, S. E. Hanafi, (2012) “Artificial Immune System Inspired Intrusion Detection System Using Genetic Algorithm”, Informatica, Vol. 36, pp. 347 358.

24. F. Barani, (2014) "A hybrid approach for dynamic intrusion detection in ad hoc networks using genetic algorithm and artificial immune system," Iranian Conference on Intelligent Systems (ICIS), pp.1 6.

25. P. K. Harmer, P. D. Williams, G. H. Gunsch, G. B. Lamont, (2002) “An Artificial Immune System Architecture for Computer Security Applications”, IEEE transactions on evolutionary computation, Vol. 6, No. 3, pp. 252¬ 280.

Received on 20.05.2020 Accepted on 14.06.2020

Int. J. Tech. 2020; 10(1):47-52.

DOI: 10.5958/2231-3915.2020.00009.7