Skip to main content

Anjan Kumar Ayyadapu

Followers

6

Following

13

Co-author

1

Public Views

Anjan Kumar Reddy Ayyadapu is a Big Data Solutions Architect at Cloudera, specializing in leading Edge to AI Platform Solutions. He has significantly contributed to digital transformation for major enterprises by delivering innovative solutions on hybrid data platforms, utilizing generative AI and secure data management. Anjan holds numerous certifications (from various providers like Amazon Web Services, IBM, DataBricks, Stanford University, Google Cloud, and the Project Management Institute (PMI)), including IBM AI Engineering Professional, IBM Applied AI Professional, AWS Certified Solution Architect Professional, and AWS Certified Machine Learning Specialist. He has expertise in Cyber Security Administration across both private and public clouds like AWS and GCP.Anjan earned his Master of Science from the University of South Alabama and a Bachelor of Technology from Jawaharlal Nehru Technological University. His research focuses on Artificial Intelligence, Machine Learning, and Deep Learning, with applications primarily in healthcare and recently in insurance. Besides his technical roles, Anjan is an expert mentor, keynote speaker, reviewer, judge for the Globee Awards, LinkedIn influencer, and AI researcher. He has authored multiple articles and holds several patents.

less

Uploads

Papers by Anjan Kumar Ayyadapu

CYBER THREAT MITIGATION THROUGH AI-ENABLED BIG DATA ANALYSIS IN CLOUD ADMINISTRATION

JOURNAL OF BASIC SCIENCE AND ENGINEERING, 2021

A data-driven threat model (d-TM) for cloud-based ecosystems is presented in this study, with a f... more A data-driven threat model (d-TM) for cloud-based ecosystems is presented in this study, with a focus on a thorough method of detecting and evaluating risks at every stage of data processing. Threat layers, actors, and a shared knowledge base are all included in the d-TM framework, which offers an organized threat analysis procedure that is assessed using a case study. The method emphasizes how important data is to corporate operations and how important it is to evaluate security risks in a comprehensive way when moving to cloud environments. risks are examined at every layer-agent, network, compute, application, and storage-by using a tier-based paradigm, which guarantees that risks are examined regardless of where the data is stored. Additionally, the model uses extensive knowledge bases including MITRE CWE, CAPEC, and NIST SP 800-53 for threat analysis and detects various threat actors, such as business users, operators, systems, and malicious actors. The steps of threat detection, mitigation, data collecting, and analysis make up the threat analysis process, which offers a methodical way to handle security risks related to cloud computing.

A COMPREHENSIVE FRAMEWORK FOR AI-BASED THREAT INTELLIGENCE IN CLOUD CYBER SECURITY

JOURNAL OF BASIC SCIENCE AND ENGINEERING, 2019

In the realm of cloud cyber security, the evolution of AI-based threat intelligence has become pi... more In the realm of cloud cyber security, the evolution of AI-based threat intelligence has become pivotal in safeguarding digital assets against increasingly sophisticated threats. This paper proposes a comprehensive framework for leveraging artificial intelligence (AI) to enhance threat intelligence capabilities within cloud environments. The framework integrates various stages of threat intelligence, including data collection, preprocessing, and feature engineering, with advanced AI and machine learning techniques such as supervised and unsupervised learning, and deep learning models. Key components include the threat intelligence lifecycle of detection, analysis, and mitigation, supported by diverse data sources like network traffic, user activity logs, and external threat feeds. Integration with existing security systems, evaluation metrics, and realworld case studies highlight practical implementations and successes. Challenges such as data privacy, scalability, and model interpretability are discussed, with future directions focusing on AI advancements and collaborative efforts to address evolving threats.

DYNAMIC RISK ASSESSMENT IN CLOUD ENVIRONMENTS USING AI-DRIVEN BIG DATA TECHNIQUES

JOURNAL OF BASIC SCIENCE AND ENGINEERING, 2020

This broad study analyzed danger request models and cloud security models as well as the befuddli... more This broad study analyzed danger request models and cloud security models as well as the befuddling subject of AI execution in the security domain. Strangely, we found proof of a positive connection between's the size of the training dataset and the model's ensuing presentation in the field of cloud security. Moreover, notwithstanding the way that dataset variety considerably affected execution, an intriguing model was noticed: bigger datasets would by and large show less assortment. By zeroing in on danger request, our examination uncovered the reasonable benefits of various AI models. Specifically, Brain Associations ended up being exceptionally viable in recognizing Phishing dangers, while Decision Trees ended up being profoundly enticing in distinguishing Malware. This exhaustive comprehension of model suitability across numerous security issues uplifts our consciousness of the extensive variety of AI applications in security settings.

DEFENDING THE CLOUD: HOW AI AND ML ARE REVOLUTIONIZING CYBERSECURITY

by Anjan Kumar Ayyadapu and Abhilash Reddy

Journal of Research Administration, 2019

This study explores how machine learning (ML) and artificial intelligence (AI) might strengthen c... more This study explores how machine learning (ML) and artificial intelligence (AI) might strengthen cybersecurity defenses in cloud computing environments. The sophistication and reach of cyber threats are growing, making traditional security methods inadequate. However, proactive threat detection, quick response times, and flexible defenses are made possible by AI and ML, which present a viable answer. Through the examination of large datasets, these technologies are able to identify irregularities and trends that may point to future attacks, allowing for the mitigation of risks in advance. This research highlights how AI and ML are changing cybersecurity techniques and how they can help make cloud-based security infrastructures more resilient and effective. It also covers how AI and ML may improve cloud security by giving businesses the ability to proactively identify, counter, and respond to new and emerging cyberthreats. This allows them to take advantage of cloud computing's flexibility and scalability while maintaining strong security protocols.

SECURING MULTI-CLOUD ENVIRONMENTS WITH AI AND MACHINE LEARNING TECHNIQUES

by Anjan Kumar Ayyadapu and Abhilash Reddy

Chelonian Conservation And Biology, 2021

This paper explores the security challenges faced in multi-cloud environments and how machine lea... more This paper explores the security challenges faced in multi-cloud environments and how machine learning (ML) can be used to address them. Multi-cloud environments offer businesses flexibility and scalability, but also introduce complexities in securing data and applications. The paper discusses the challenges of distributed data, identity and access management, interoperability, and compliance. It then explores how multi-cloud security strategies can be implemented to mitigate these risks. Finally, the paper examines the role of machine learning in enhancing multi-cloud security by providing anomaly detection, intrusion prevention, and data encryption.

AUTOMATING INCIDENT RESPONSE: AI-DRIVEN APPROACHES TO CLOUD SECURITY INCIDENT MANAGEMENT

by Anjan Kumar Ayyadapu and Abhilash Reddy

Chelonian Conservation And Biology, 2020

The increasing integration of cloud computing into modern computerised infrastructures has made s... more The increasing integration of cloud computing into modern computerised infrastructures has made security more crucial in the fight against dangers such as data breaches and administrative disruptions. The complexity of cloud environments challenges traditional incident response tactics, which has led to the rise of artificial intelligence (AI) solutions. With a focus on 2020, this study explores AI-driven approaches to cloud security incident management. It covers evolving risks to cloud security and encourages proactive response techniques. Associations can work on event identification, investigation, and objective in real-time by using AI calculations. Important topics bear in mind the role AI plays in threat intelligence, example recognition, and anomaly detection in cloud environments. AI-driven automation makes incident containment easier and decreases the impact of interruptions on operations. Issues with data security and algorithmic inclination, for instance, are looked at.

Securing Cloud Data with a Hybrid Approach Machine Learning and Cryptosystems

The Patent Office Journal No. 06/2024, 2024

SECURING CLOUD DATA WITH A HYBRID APPROACH: MACHINE LEARNING AND CRYPTOSYSTEMS A method for the d... more SECURING CLOUD DATA WITH A HYBRID APPROACH: MACHINE LEARNING AND CRYPTOSYSTEMS A method for the development To achieve higher levels of security inside a cloud environment, one of the most critical parts of cloud service provisioning is preventing data breaches caused by unauthorized access to personal information. Many security procedures have still to be improved to an appropriate level. There are several approaches for achieving data and information security, such as cryptography and steganography. This study presents a novel technique to mutual authentication that use a pre-trained model of a convolutional neural network (CNN) to detect illicit internet activities. There are two types of prime field operations: one that involves field multiplication and field squaring of elliptic curve point coordinates, and another that involves field addition, field doubling, and field subtraction of elliptic curve point coordinates. The method for countering a subchannel attack on the elliptic curve cryptosystem described in the present invention is advantageous in that it improves cryptosystem stability while lowering the system's computational overhead.

Privacy-Preserving Techniques in AI-Driven Big Data Cyber Security for Cloud

Chelonian Conservation and Biology, 2022

Artificial intelligence (AI) and big data technologies are evolving at a rapid pace, completely c... more Artificial intelligence (AI) and big data technologies are evolving at a rapid pace, completely changing the cybersecurity landscape in cloud environments. But this advancement also presents previously unheard-of difficulties, namely with regard to privacy enormous volumes of sensitive data. This abstract investigates privacy context of cloud-based AI-driven big data cybersecurity. Strong as more and more businesses rely on cloud services to handle and keep their data. This study explores cutting-edge techniques and tools designed to protect user privacy while utilising AI to analyses large amounts of data for cybersecurity p range of organizations, including banks, supply chains, e producing enormous amounts of data. based records, shut circuit TV streaming, and different means. Online entertainment and cell phones make tremendous measures of data consistently. To aid in direction, the monstrous measures of data delivered by the various sources can be handled and analyzed. Data examination, in any case, is defenseless against privacy encroachment. Suggestion frameworks, which are habitually utilized by propose things to clients based on their buying propensities, are one utilization o examination that could bring about deduction assaults.

OPTIMIZING INCIDENT RESPONSE IN CLOUD SECURITY WITH AI AND BIG DATA INTEGRATION

Chelonian Conservation and Biology, 2023

This study investigates how to combine big data analytics and artificial intelligence (AI) to opt... more This study investigates how to combine big data analytics and artificial intelligence (AI) to optimize incident response in cloud security. Strong security measures are becoming essential as more and more businesses use cloud environments. The study looks can work together to improve incident response systems by using real predictive analytics, and machine learning. By integrating AI, security events in the cloud can be proactively identified and mitigated, red operations. Big Data technologies, on the other hand, manage a variety of datasets with efficiency and offer insights into patterns, abnormalities, and possible security breaches. A

Enhancing Cloud Security With Ai-Driven Big Data Analytics

International Neurourology Journal, 2023

This broad review investigated the perplexing field of AI performance in the security region, inc... more This broad review investigated the perplexing field of AI performance in the security region, including threat order models and cloud security models. Curiously, in the domain of cloud security, our exploration uncovered areas of strength for a connection between the size of the training dataset and the model's performance from there on. Besides, notwithstanding the way that dataset variety significantly affected performance, a remarkable example was noticed: greater datasets would in general show less assortment. Directing our concentration toward threat order, our exploration uncovered the unmistakable benefits of various AI models. Specifically, Brain Organizations ended up being very viable at perceiving Phishing threats, while Choice Trees ended up being extremely compelling at recognizing Malware. Our consciousness of the extensive variety of AI applications in security settings is improved by this detailed comprehension of model viability across different security concerns.

Secure Cloud Infrastructures: A Machine Learning Perspective

International Neurourology Journal, 2022

A computing paradigm known as "cloud computing" offers end users scalable, measurable, and on-dem... more A computing paradigm known as "cloud computing" offers end users scalable, measurable, and on-demand services. Nowadays, practically all businesses rely heavily on computing technology for infrastructure, development platforms, cost savings, data processing, data analytics, and other purposes. This work focuses on using machine learning (ML) approaches to advance industry standards for cloud computing security. The goals of the ML study are met by the identification of these ten crucial features. Additionally, the goal of this research is to create a workable plan for anticipating machine learning use in an Industrial Cloud context with respect to privacy and trust concerns. By using F1 scores, R.O.C. curves, confusion matrices, and validation matrices of precision, accuracy, and recall values, the effectiveness of the used models is evaluated. The findings showed that the X.G.B. model performed better than all other models for each matrix, with 98.60% accuracy, 98.70% precision, 98.70% recall, and 98.60% F1 score. This study demonstrates how machine learning techniques may improve cloud computing security for many sectors. It highlights how important it is to carry out ongoing research and development in order to produce more sophisticated and effective cloud computing security solutions. By investigating diverse machine learning models, algorithms, and tactics, the study advances the creation of sophisticated security frameworks customised for cloud-based systems. The goal of this interdisciplinary approach is to offer solutions and insights for maintaining strong security measures in the quickly changing cloud computing environment.

CYBER THREAT MITIGATION THROUGH AI-ENABLED BIG DATA ANALYSIS IN CLOUD ADMINISTRATION

JOURNAL OF BASIC SCIENCE AND ENGINEERING, 2021

A data-driven threat model (d-TM) for cloud-based ecosystems is presented in this study, with a f... more A data-driven threat model (d-TM) for cloud-based ecosystems is presented in this study, with a focus on a thorough method of detecting and evaluating risks at every stage of data processing. Threat layers, actors, and a shared knowledge base are all included in the d-TM framework, which offers an organized threat analysis procedure that is assessed using a case study. The method emphasizes how important data is to corporate operations and how important it is to evaluate security risks in a comprehensive way when moving to cloud environments. risks are examined at every layer-agent, network, compute, application, and storage-by using a tier-based paradigm, which guarantees that risks are examined regardless of where the data is stored. Additionally, the model uses extensive knowledge bases including MITRE CWE, CAPEC, and NIST SP 800-53 for threat analysis and detects various threat actors, such as business users, operators, systems, and malicious actors. The steps of threat detection, mitigation, data collecting, and analysis make up the threat analysis process, which offers a methodical way to handle security risks related to cloud computing.

A COMPREHENSIVE FRAMEWORK FOR AI-BASED THREAT INTELLIGENCE IN CLOUD CYBER SECURITY

JOURNAL OF BASIC SCIENCE AND ENGINEERING, 2019

In the realm of cloud cyber security, the evolution of AI-based threat intelligence has become pi... more In the realm of cloud cyber security, the evolution of AI-based threat intelligence has become pivotal in safeguarding digital assets against increasingly sophisticated threats. This paper proposes a comprehensive framework for leveraging artificial intelligence (AI) to enhance threat intelligence capabilities within cloud environments. The framework integrates various stages of threat intelligence, including data collection, preprocessing, and feature engineering, with advanced AI and machine learning techniques such as supervised and unsupervised learning, and deep learning models. Key components include the threat intelligence lifecycle of detection, analysis, and mitigation, supported by diverse data sources like network traffic, user activity logs, and external threat feeds. Integration with existing security systems, evaluation metrics, and realworld case studies highlight practical implementations and successes. Challenges such as data privacy, scalability, and model interpretability are discussed, with future directions focusing on AI advancements and collaborative efforts to address evolving threats.

DYNAMIC RISK ASSESSMENT IN CLOUD ENVIRONMENTS USING AI-DRIVEN BIG DATA TECHNIQUES

JOURNAL OF BASIC SCIENCE AND ENGINEERING, 2020

This broad study analyzed danger request models and cloud security models as well as the befuddli... more This broad study analyzed danger request models and cloud security models as well as the befuddling subject of AI execution in the security domain. Strangely, we found proof of a positive connection between's the size of the training dataset and the model's ensuing presentation in the field of cloud security. Moreover, notwithstanding the way that dataset variety considerably affected execution, an intriguing model was noticed: bigger datasets would by and large show less assortment. By zeroing in on danger request, our examination uncovered the reasonable benefits of various AI models. Specifically, Brain Associations ended up being exceptionally viable in recognizing Phishing dangers, while Decision Trees ended up being profoundly enticing in distinguishing Malware. This exhaustive comprehension of model suitability across numerous security issues uplifts our consciousness of the extensive variety of AI applications in security settings.

DEFENDING THE CLOUD: HOW AI AND ML ARE REVOLUTIONIZING CYBERSECURITY

by Anjan Kumar Ayyadapu and Abhilash Reddy

Journal of Research Administration, 2019

This study explores how machine learning (ML) and artificial intelligence (AI) might strengthen c... more This study explores how machine learning (ML) and artificial intelligence (AI) might strengthen cybersecurity defenses in cloud computing environments. The sophistication and reach of cyber threats are growing, making traditional security methods inadequate. However, proactive threat detection, quick response times, and flexible defenses are made possible by AI and ML, which present a viable answer. Through the examination of large datasets, these technologies are able to identify irregularities and trends that may point to future attacks, allowing for the mitigation of risks in advance. This research highlights how AI and ML are changing cybersecurity techniques and how they can help make cloud-based security infrastructures more resilient and effective. It also covers how AI and ML may improve cloud security by giving businesses the ability to proactively identify, counter, and respond to new and emerging cyberthreats. This allows them to take advantage of cloud computing's flexibility and scalability while maintaining strong security protocols.

SECURING MULTI-CLOUD ENVIRONMENTS WITH AI AND MACHINE LEARNING TECHNIQUES

by Anjan Kumar Ayyadapu and Abhilash Reddy

Chelonian Conservation And Biology, 2021

This paper explores the security challenges faced in multi-cloud environments and how machine lea... more This paper explores the security challenges faced in multi-cloud environments and how machine learning (ML) can be used to address them. Multi-cloud environments offer businesses flexibility and scalability, but also introduce complexities in securing data and applications. The paper discusses the challenges of distributed data, identity and access management, interoperability, and compliance. It then explores how multi-cloud security strategies can be implemented to mitigate these risks. Finally, the paper examines the role of machine learning in enhancing multi-cloud security by providing anomaly detection, intrusion prevention, and data encryption.

AUTOMATING INCIDENT RESPONSE: AI-DRIVEN APPROACHES TO CLOUD SECURITY INCIDENT MANAGEMENT

by Anjan Kumar Ayyadapu and Abhilash Reddy

Chelonian Conservation And Biology, 2020

The increasing integration of cloud computing into modern computerised infrastructures has made s... more The increasing integration of cloud computing into modern computerised infrastructures has made security more crucial in the fight against dangers such as data breaches and administrative disruptions. The complexity of cloud environments challenges traditional incident response tactics, which has led to the rise of artificial intelligence (AI) solutions. With a focus on 2020, this study explores AI-driven approaches to cloud security incident management. It covers evolving risks to cloud security and encourages proactive response techniques. Associations can work on event identification, investigation, and objective in real-time by using AI calculations. Important topics bear in mind the role AI plays in threat intelligence, example recognition, and anomaly detection in cloud environments. AI-driven automation makes incident containment easier and decreases the impact of interruptions on operations. Issues with data security and algorithmic inclination, for instance, are looked at.

Securing Cloud Data with a Hybrid Approach Machine Learning and Cryptosystems

The Patent Office Journal No. 06/2024, 2024

SECURING CLOUD DATA WITH A HYBRID APPROACH: MACHINE LEARNING AND CRYPTOSYSTEMS A method for the d... more SECURING CLOUD DATA WITH A HYBRID APPROACH: MACHINE LEARNING AND CRYPTOSYSTEMS A method for the development To achieve higher levels of security inside a cloud environment, one of the most critical parts of cloud service provisioning is preventing data breaches caused by unauthorized access to personal information. Many security procedures have still to be improved to an appropriate level. There are several approaches for achieving data and information security, such as cryptography and steganography. This study presents a novel technique to mutual authentication that use a pre-trained model of a convolutional neural network (CNN) to detect illicit internet activities. There are two types of prime field operations: one that involves field multiplication and field squaring of elliptic curve point coordinates, and another that involves field addition, field doubling, and field subtraction of elliptic curve point coordinates. The method for countering a subchannel attack on the elliptic curve cryptosystem described in the present invention is advantageous in that it improves cryptosystem stability while lowering the system's computational overhead.

Privacy-Preserving Techniques in AI-Driven Big Data Cyber Security for Cloud

Chelonian Conservation and Biology, 2022

Artificial intelligence (AI) and big data technologies are evolving at a rapid pace, completely c... more Artificial intelligence (AI) and big data technologies are evolving at a rapid pace, completely changing the cybersecurity landscape in cloud environments. But this advancement also presents previously unheard-of difficulties, namely with regard to privacy enormous volumes of sensitive data. This abstract investigates privacy context of cloud-based AI-driven big data cybersecurity. Strong as more and more businesses rely on cloud services to handle and keep their data. This study explores cutting-edge techniques and tools designed to protect user privacy while utilising AI to analyses large amounts of data for cybersecurity p range of organizations, including banks, supply chains, e producing enormous amounts of data. based records, shut circuit TV streaming, and different means. Online entertainment and cell phones make tremendous measures of data consistently. To aid in direction, the monstrous measures of data delivered by the various sources can be handled and analyzed. Data examination, in any case, is defenseless against privacy encroachment. Suggestion frameworks, which are habitually utilized by propose things to clients based on their buying propensities, are one utilization o examination that could bring about deduction assaults.

OPTIMIZING INCIDENT RESPONSE IN CLOUD SECURITY WITH AI AND BIG DATA INTEGRATION

Chelonian Conservation and Biology, 2023

This study investigates how to combine big data analytics and artificial intelligence (AI) to opt... more This study investigates how to combine big data analytics and artificial intelligence (AI) to optimize incident response in cloud security. Strong security measures are becoming essential as more and more businesses use cloud environments. The study looks can work together to improve incident response systems by using real predictive analytics, and machine learning. By integrating AI, security events in the cloud can be proactively identified and mitigated, red operations. Big Data technologies, on the other hand, manage a variety of datasets with efficiency and offer insights into patterns, abnormalities, and possible security breaches. A

Enhancing Cloud Security With Ai-Driven Big Data Analytics

International Neurourology Journal, 2023

This broad review investigated the perplexing field of AI performance in the security region, inc... more This broad review investigated the perplexing field of AI performance in the security region, including threat order models and cloud security models. Curiously, in the domain of cloud security, our exploration uncovered areas of strength for a connection between the size of the training dataset and the model's performance from there on. Besides, notwithstanding the way that dataset variety significantly affected performance, a remarkable example was noticed: greater datasets would in general show less assortment. Directing our concentration toward threat order, our exploration uncovered the unmistakable benefits of various AI models. Specifically, Brain Organizations ended up being very viable at perceiving Phishing threats, while Choice Trees ended up being extremely compelling at recognizing Malware. Our consciousness of the extensive variety of AI applications in security settings is improved by this detailed comprehension of model viability across different security concerns.

Secure Cloud Infrastructures: A Machine Learning Perspective

International Neurourology Journal, 2022

A computing paradigm known as "cloud computing" offers end users scalable, measurable, and on-dem... more A computing paradigm known as "cloud computing" offers end users scalable, measurable, and on-demand services. Nowadays, practically all businesses rely heavily on computing technology for infrastructure, development platforms, cost savings, data processing, data analytics, and other purposes. This work focuses on using machine learning (ML) approaches to advance industry standards for cloud computing security. The goals of the ML study are met by the identification of these ten crucial features. Additionally, the goal of this research is to create a workable plan for anticipating machine learning use in an Industrial Cloud context with respect to privacy and trust concerns. By using F1 scores, R.O.C. curves, confusion matrices, and validation matrices of precision, accuracy, and recall values, the effectiveness of the used models is evaluated. The findings showed that the X.G.B. model performed better than all other models for each matrix, with 98.60% accuracy, 98.70% precision, 98.70% recall, and 98.60% F1 score. This study demonstrates how machine learning techniques may improve cloud computing security for many sectors. It highlights how important it is to carry out ongoing research and development in order to produce more sophisticated and effective cloud computing security solutions. By investigating diverse machine learning models, algorithms, and tactics, the study advances the creation of sophisticated security frameworks customised for cloud-based systems. The goal of this interdisciplinary approach is to offer solutions and insights for maintaining strong security measures in the quickly changing cloud computing environment.