GET THE APP

Cyber security risks in identity and access management using an adaptive trust authentication protocol
Journal of Computer Science & Systems Biology

Journal of Computer Science & Systems Biology

ISSN: 0974-7230

Open Access

Cyber security risks in identity and access management using an adaptive trust authentication protocol


13th Global Summit on Artificial Intelligence and Neural Networks

March 14, 2025 | Webinar

Premsai Ranga

Technical Fellow in Cyber security and Identity Management, USA

Keynote: J Comput Sci Syst Biol

Abstract :

Statement of the Problem: Identity and Access Management (IAM) systems are critical for safeguarding organizational infrastructure by ensuring that only authorized users access sensitive information and resources. However, traditional IAM protocols often struggle to detect advanced threats such as identity spoofing, privilege escalation, and unauthorized access through stolen credentials. This paper proposes an adaptive trust authentication protocol that addresses these challenges by integrating deep learning-based anomaly detection, user behavior analytics (UBA), and multi-factor authentication (MFA) into the access control process. The protocol utilizes behavioral biometrics and dynamic access control to continuously monitor user actions in real-time, detecting deviations from typical usage patterns indicative of potential threats. A user trust score is dynamically generated based on real-time behavior analysis and MFA results, while behavior patterns are further evaluated using a deep control convolutional network. By combining the trust score with behavioral analytics, the system initiates secure and context-aware authentication of sensitive financial data. Extensive testing of the proposed protocol demonstrates its effectiveness in mitigating internal and external cyber security risks, significantly improving detection accuracy and reducing false positives. The novelty of this approach lies in its seamless integration of advanced behavioral analytics, deep learning, and adaptive authentication strategies, offering a robust, scalable, and resilient solution for modern IAM systems. Index Termsā??Identity and Access Management, Multi-Factor Authentication, Deep Learning, Financial Data Security, deep control convolutional network

Biography :

Premsai Ranga is a seasoned professional with over 9 years of experience in Identity and Access Management (IAM), cyber security, and technology leadership. His expertise lies in safeguarding critical systems and sensitive data through innovative security solutions, driven by a passion for continuous learning and a commitment to creating secure digital ecosystems. Premasaiā??s notable achievements include spearheading the implementation of Zero Trust Architecture at Inovalon Inc., reducing insider threats by over 95%. His contributions to projects like the InovalonOne Platform and NLPAaS have been instrumental in revolutionizing access control and advancing security frameworks in the healthcare sector. Currently, Premsai oversees IAM frameworks for a large-scale organization, managing over 10,000 users, 500+ applications, and 2,000+ APIs. His responsibilities encompass designing IAM policies, managing user access, implementing multi-factor authentication, and collaborating with IT and security teams to ensure seamless integration. He holds a masterā??s degree in computers and information systems with a 3.81 GPA and prestigious certifications, including CISA and Azure Security Engineer Associate, which reinforce his expertise in IAM and cyber security. Beyond his professional endeavors, Premasai is passionate about community engagement. He volunteers with organizations such as First Fruits Farm and Moveable Feast and contributes as a volunteer auditor for ISACA. Looking ahead, he aspires to take on senior leadership roles to influence strategic technology decisions and mentor the next generation of IAM and cybersecurity leaders. With a strong foundation in technical knowledge and a dedication to humanitarian values, Premasai Ranga strives to build a safer, more secure digital world for individuals and organizations alike.

Google Scholar citation report
Citations: 2279

Journal of Computer Science & Systems Biology received 2279 citations as per Google Scholar report

Journal of Computer Science & Systems Biology peer review process verified at publons

Indexed In

 
arrow_upward arrow_upward