Vaishnavi Gudur
Biography
Vaishnavi Gudur is a seasoned Senior Software Engineer based in Seattle, Washington, with extensive experience in designing and implementing scalable, secure, and user-centric enterprise applications. Currently contributing to Microsoft Corporation, she has played a pivotal role in enhancing the security features of Microsoft Teams, safeguarding over 145 million global users against phishing threats. Her expertise lies in full-stack development, system design, and performance optimization, with a focus on improving user experience and operational efficiency.
Prior to her tenure at Microsoft, Vaishnavi led impactful engineering projects at Expedia Group and Cerner Corporation, where she optimized enrollment systems, developed scalable APIs, and enhanced healthcare software performance. She holds a Master?s degree in Computer Science with a specialization in Database Systems from the Illinois Institute of Technology, Chicago, and a Bachelor's degree in Information Technology from Mumbai University.
Vaishnavi is also an active researcher and contributor to the tech community, with forthcoming book chapters on cloud technologies, AI-driven cybersecurity, and agentic AI in healthcare. She has presented at leading conferences, served as a peer reviewer for journals and book chapters, and judged industry awards in AI and software innovation. Her interests include explainable AI, secure and scalable distributed systems, and human-centered system design.
Research Interest
Vaishnavi Gudur?s research interests focus on building strong and scalable systems using full-stack architecture and distributed computing. She is interested in using artificial intelligence to improve security and ensure systems can protect themselves from threats. She also explores how to make AI more understandable and user-friendly through explainable AI and human-centered design. Vaishnavi cares about responsible use of AI, looking into how it can be governed and managed over time. In addition, she is interested in cloud computing, especially how it can be made more sustainable while supporting advanced technologies like generative AI.
Abstract
Cybersecurity is facing increasingly sophisticated and fast-evolving threats that traditional defenses struggle to keep up with. This paper proposes a novel AI-driven cybersecurity framework that leverages machine learning (ML) and generative artificial intelligence (GenAI) to enhance threat detection, automate incident response, improve anomaly detection, and strengthen zero-day exploit prevention. The framework addresses several key challenges faced by current AI-based security systems, such as high false positive rates, poor detection of novel attacks, slow response times, and integration difficulties.
Our proposed solution combines generative models?such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs)?with advanced deep learning techniques and large language model (LLM) methodologies. We demonstrate how synthetic data generation and generative modeling enable the detection of unusual behavior and unknown threats before they manifest. Additionally, we explore how reinforcement learning and automation facilitate rapid and effective containment of incidents.
A proof-of-concept simulation illustrates that the proposed framework significantly improves both detection accuracy and response speed compared to conventional cybersecurity solutions. Furthermore, the framework seamlessly integrates with existing tools such as Security Information and Event Management (SIEM) and Security Orchestration, Automation, and Response (SOAR) platforms, while also ensuring data privacy.
The results suggest that incorporating GenAI can lead to more adaptive and intelligent cyber defense systems. We conclude by discussing the potential benefits, current limitations?including risks related to adversarial machine learning and the need for explainable AI?and future research directions for large-scale application of generative AI in cybersecurity.
