Impact Of Artificial Intelligence In Security Testing Author: Sallaram Priyanka Reddy,Software Engineer Co-Author: R.Bhanu Prakash Meher, Software Engineer Capgemini India Pvt Ltd

ABSTARCT The testing industry is looking for innovative ways to optimize testing efforts and cost. One of the ways is usage of tools and accelerators. The usage of these tools along with artificial intelligence has proved to be a lot effective. This paper attempts to explain why Testing industry needs Artificial Intelligence to attain Security , accuracy, repeatability and speed. Initial Concepts Some Strategies ->What is Artificial Intelligence? ->What is Machine Learning? ->What is Cognitive Computing? Microsoft Risk Detection Tool IBM Watson Deep Q&A Google DeepMind Conclusion -> Business Benefits -> Increase in Quality

Challenges Did You know? 90%: Percentage of web apps with vulnerabilities caused by security functions. 16,081: Total number of vulnerabilities detected in 2015 in 2,484 applications. Gartner Says More than 75 Percent of Mobile Applications will Fail Basic Security Tests

What is Artificial Intelligence? ->According to the father of Artificial Intelligence, John McCarthy, it is “The science and engineering of making intelligent machines, especially intelligent computer programs”. ->AI is accomplished by studying how human brain thinks, and how humans learn, decide, and work while trying to solve a problem, and then using the outcomes of this study as a basis of developing intelligent software and systems.

What is Machine Learning? ->Machine learning is a type of artificial intelligence (AI) that provides computers with the ability to learn without being explicitly programmed. Machine learning focuses on the development of computer programs that can change when exposed to new data. ->Artificial Intelligence is the broader concept of machines being able to carry out tasks in a way that we would consider “smart”. ->While, Machine Learning is a current application of AI based around the idea that we should really just be able to give machines access to data and let them learn for themselves.

What is Cognitive Computing? ->Cognitive computing is the simulation of human thought processes in a computerized model. Cognitive computing involves self-learning systems that use data mining, pattern recognition and natural language processing to mimic the way the human brain works. ->Cognitive systems are probabilistic, meaning they are designed to adapt and make sense of the complexity and unpredictability of unstructured information. They can “read” text, “see” images and “hear” natural speech. They do not offer definitive answers. In fact, they do not “know” the answer. Rather, they are designed to weigh information and ideas from multiple sources, to reason, and then offer hypotheses for consideration. A cognitive system assigns a confidence level to each potential insight or answer.

Scope Of AI in Security Testing ->Software Testing (ST) is an investigation process which attempts to validate and verify the alignment of a software system’s attributes and functionality with its intended goals. ->The main idea for software testing lies on the decision system based on artificial intelligent approach and is built on algorithm with the neural network usage. We can generally summarize the self-learning of the system from the below mentioned equation: (Training data Test Data) + (Learning Machine) = Analysed data for prediction -> What if there was one a mechanism to intelligently derive areas that one should test and secondly identify repetitive patterns based on data that could be automated. Enter artificial intelligence and machine learning

Contd…. -> Microsoft Security Risk Detection is previously known as Project Springfield, is a cloud-based tool that can be used to look for bugs and other security vulnerabilities in the software they are preparing to release or use. This detection service uses artificial intelligence to ask a series of “what if” questions to try to root out what might trigger a crash and signal a security concern. -> David Molnar, a Microsoft Researcher said that this service is helpful for companies that are going through a massive digital transformation, incorporating technology into processes that used to either be done manually or utilized much simpler technology. -> Regression testing is complex when the interface is reformed. It is possible that many of the current test cases cannot be performed with the new interface. This can bound automation in regression testing and therefore considerably increase the cost of regression testing. That’s where artificial intelligence can be introduced.

Contd…. ->Ant Colony Optimization (ACO), Genetic Algorithm (GA), Tabu search (TB), Bee Colonoy, Fuzzy Approach, Data mining Concept and many more AI techniques. They are used in various processes of the security testing, quality and reliability like test sequence generation, automation of testing, quantification of quality, checking reliability of the system -> The five senses of Artificial Intelligence (watch, remember, think, talk, act) as a useful framework for businesses exploring automation solutions. To think of AI as a single thing—instead, it is the integration of several different solutions and capabilities. You need to plan for all five senses working together if you want to replicate human intelligence. Research is also underway to look at “using artificial intelligence to analyze and protect urban infrastructure,” which could help future smart cities to identify hacking threats and build countermeasures automatically. ->This new “machine partner” can delight and empower us, but for some, these changes can cause concern to both the security of their current roles and their future required skills and responsibilities.

Overall Profit to the Organization Benefits To Business Overall Profit to the Organization

Early Adopters

Author Biography References & Appendix 1. Watson, Thomas Jr. IBM Archives. https://www-03.ibm.com/ ibm/history/exhibits/watsonjr/watsonjr_quoted.html 2.https://www.forbes.com/sites/bernardmarr/2016/12/06/what-is-the-difference-between-artificial-intelligence-and-machine-learning/#50ab241c2742 3. http://www.investopedia.com/news/new-advances-ai-google-acquisition-deepmind-goog-aapl/ 4.https://www.forbes.com/sites/bryanpearson/2017/01/30/using-artificial-intelligence-both-in-apps-and-in-the-aisles/#42aee1297a3a 5. https://techbeacon.com/32-app-sec-stats-you-should-be-tracking 6. http://www.gartner.com/newsroom/id/2846017 7. https://www.capgemini.com/2017/08/is-cybersecurity-the-sixth-sense-of-ai/   Priyanka Sallaram: is a Software Engineer with the Insurance business unit of Capgemini and can be reached at Sallaram.reddy@capgemini.com Bhanu Prakash Meher : is a Software Engineer with the Insurance business unit of Capgemini and can be reached at regulagedda.meher@capgemini.com

Thank You!!!