2026Conference
Open to full-time roles starting May 2026
Hi, I'm Aravind Cheruvu.
Ph.D. candidate in Computer Science at Virginia Tech, researching security and generative AI.
I work on attacks and defenses for Large Language Models and Agentic AI, with a focus on conversational systems. Previously a GenAI Research Intern at Samsung Research America and a Senior Consultant at Deloitte (4.5 years).
Blacksburg, VA
Virginia Tech
Advised by Dr. Danfeng Yao
About
A bit about me
Hi! I am Aravind Cheruvu, a Ph.D. candidate in the Computer Science department at Virginia Tech, advised by Dr. Danfeng Yao. As a Generative AI enthusiast, my research focuses on security and generative AI. I am honored to have received the Pratt Fellowship from the CS department.
My research investigates attacks and defenses within Large Language Models (LLMs) and Agentic AI, with a core focus on conversational AI systems. Specifically, I examine and mitigate data poisoning attacks on LLMs during model customization. Furthermore, I explore defense mechanisms against novel threat vectors emerging from Agentic AI. My background also includes work in Computer Vision, specifically involving deepfakes, GANs, and diffusion models.
I worked as a GenAI Research Intern at Samsung Research America (SRA) in Fall 2025. I also have 4.5 years of consulting experience, during which I worked on several large-scale projects with US-based clients. At Deloitte Consulting, I specialized as an Oracle Payroll Implementation Specialist. I completed my Bachelor's in Information Technology in 2016 from VNR VJIET, Hyderabad (affiliated with JNTU), where I gained research experience in Temporal Data Mining and Network Security.
Latest News
What's new
Recent papers, talks, awards, and milestones.
- My paper "Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI" has been accepted to CODASPY 2026.
- I gave a research talk at UIUC invited by Dr. Xiaojing Liao and Dr. Luyi Xing in Dec 2025.
- I worked as a GenAI Research Intern at Samsung Research America (SRA) in Fall 2025.
- I have successfully passed my Ph.D. Preliminary exam.
- I attended The Amazon - Virginia Tech Initiative for Efficient and Robust Machine Learning Fall retreat in Oct 2024.
- I attended IEEE S&P 2024 as a coauthor in San Francisco in May 2024.
- I have successfully passed my Ph.D. Qualifier exam with a perfect score.
- Received the "Pratt Fellowship" from the Department of Computer Science.
- Awarded the CCI SWVA Cyber Innovation Scholarship from Commonwealth Cyber Initiative (CCI) for FY 23 and 24.
- Presented my paper "A First Look at Toxicity Injection Attacks on Open-domain Chatbots" at ACSAC 2023 in Austin, TX in Dec 2023.
- Received the "Best Poster award at CCI researcher showcase" - Future cybersecurity leaders showcase research.
- News interview at WDBJ7 - "Virginia Tech research aims to reduce toxic language from artificial intelligence."
- News interview to VPM News Focal Point - "Artificial intelligence: What are the risks and benefits?"
Research Interests
What I work on
Topics I'm actively researching or have deep experience with.
Security & Generative AI
Large Language Models (LLMs)
Conversational AI Systems
Computer Vision & Deepfakes
Temporal Data Mining
Network Security
Publications
Selected publications & patents
Full list available on Google Scholar. Author names with bold indicate me.
2025Preprint
2024Conference
2023Conference
A First Look at Toxicity Injection Attacks on Open-domain Chatbots ACSAC 2023
Annual Computer Security Applications Conference, Austin, TX, December 2023
2018Conference
Feature clustering for anomaly detection using improved fuzzy membership function
International Conference on Engineering & MIS, 2018
2017Journal
A dissimilarity measure for mining similar temporal association patterns
IADIS International Journal on Computer Science and Information Systems, 2017
Patents
Patents
2020Patent
System and Method for Diagnosis of Diseases From Medical Images
A novel machine learning implementation of a COVID-19 detection system using chest X-rays.
2018Patent
System and Method to Generate Time-Profiled Temporal Pattern Tree
A novel temporal tree structure for discovering temporal association rules in large datasets.
Experience
Where I've worked
Roles in research and consulting across the past several years.
-
Aug 2025 - Nov 2025
GenAI Research Intern
Samsung Research America (SRA)- Generative AI / LLMs / Health Applications: Designed and developed Generative AI applications for digital health and wellness, delivering adaptive coaching, personalized recommendations, and context-aware health insights.
- Backend Prototyping / RAG / Cloud Integration: Developed scalable backend pipelines and RESTful APIs to process multi-modal health data from smartphones and wearables, enabling RAG-based AI assistants that provide real-time, evidence-informed guidance.
- Cross-Functional Research / Explainable AI / Clinical Collaboration: Partnered with AI scientists, clinicians, and human-factors researchers to co-innovate digital health solutions. Implemented AI-driven insights and explainable visualizations translating wearable and time-series analytics into actionable wellness feedback. Supported pilot studies to validate GenAI-based health coaching and conversational frameworks.
-
Aug 2021 - Present
Graduate Research Assistant
Virginia Tech- Research focus: Security and Generative AI under the supervision of Dr. Danfeng Yao.
- Projects: Toxicity injection attacks on chatbots, deepfake detection, and LLM safety alignment.
- Achievements: Published papers at top-tier conferences (ACSAC 2023, IEEE S&P 2024, CODASPY 2026).
-
Jun 2021 - Jul 2021
Senior Consultant
Deloitte Consulting- Certified Oracle HCM Cloud transformation consultant with 4.5 years of demonstrated techno-functional expertise specialized in capturing business use cases, understanding requirements, and performing fit-gap analysis to design scalable 50+ Technical RICEF objects and business process solutions.
- Strategized and executed Payroll Parallel/Reconciliation testing cycles for 5 successful client implementations to uncover system implementation defects, understand financial and business process impacts of Go-live and Post Production, and recommend mitigation strategies.
-
Sep 2018 - Jun 2021
Consultant
Deloitte ConsultingPayroll Reconciliation:
- Led planning and execution of Payroll Compare cycles for multiple clients to perform trend analysis of $MM employee payrolls, test data integrity, and understand Go-Live and Post-Production impacts of Payroll, Benefits, Time (TL), Absence, and Compensation systems using SQL and Excel analytics.
- Developed and streamlined a Payroll Compare Analysis and Executive Reporting Tool which extracts and uses HR and Payroll run data between Legacy and simulated Test systems to produce Payroll Compare reports and Executive Dashboards for extensive payroll data analysis.
Payroll RICEF:
- Supported Payroll BR100 configurations and coordinated and executed SIT and UAT testing cycles.
-
Dec 2016 - Aug 2018
Business Analyst
Deloitte ConsultingTechnical Developer:
- Worked as a technical team member implementing key out-of-the-box integrations using HCM Extracts to Kronos and Benefits systems, BI Publisher reports using eText and RTF templates, and developed Payroll Fast Formulas.
-
Jun 2016 - Sep 2016
Assistant System Engineer - Trainee
Tata Consultancy Services- Trained in E-Business Suite, Oracle Business Intelligence EE, and Oracle Data Integrator tools.
Education
Academic background
-
Aug 2021 - Present
Ph.D. in Computer Science (M.S. along the way)
Virginia Polytechnic Institute and State University (Virginia Tech)- CGPA: 3.75
- Advisor: Dr. Danfeng Yao
- Research focus: Security and Generative AI
- Status: Ph.D. Candidate (Passed Ph.D. Preliminary exam)
Graduate courseworkData Analytics Deep Learning Hot Topics in Security and AI Theory of Algorithms Advanced Machine Learning Security Risks of Generative AI Defenses Against ML Powered Adversaries -
Sep 2012 - May 2016
Bachelor's in Information Technology
Jawaharlal Nehru Technological University (VNR VJIET)- CGPA: 8.51 / 10.0
- Achievement: Gold Medal for best outgoing student from the Department of I.T.
- Specialization: Information Technology with focus on Data Mining and Network Security
Relevant courseworkData Structures & Algorithms Database Management Systems Computer Networks Software Engineering Data Mining & Warehousing Network Security Operating Systems Computer Graphics
Achievements
Academic honors
- Ph.D. Preliminary Exam: Passed - now a Ph.D. candidate.
- Ph.D. Qualifier Exam: Passed with a perfect score.
- Pratt Fellowship: Received from the Department of Computer Science at Virginia Tech.
- CCI SWVA Cyber Innovation Scholarship: Awarded for FY 23 and 24 from Commonwealth Cyber Initiative (CCI).
- Gold Medal: Best outgoing student from the Department of Information Technology at VNR VJIET.
Skills
Technical toolkit
Languages, frameworks, and platforms I work with regularly.
NLP & Generative AI
Computer Vision & GenAI
ML Libraries & Frameworks
Programming Languages
Developer Tools
Systems & Frameworks
Oracle (Industry)
Research Skills
Certifications & Training
Talks & Media
Presentations & coverage
Conference talks, posters, and media interviews.
A First Look at Toxicity Injection Attacks on Open-domain Chatbots
Watch on YouTubeRecent Advances in Deepfake Image Detection in an Evolving Threat Landscape
Research talk at UIUC
Best Poster Award - CCI Researcher Showcase
News coverageVirginia Tech research aims to reduce toxic language from artificial intelligence
Watch interviewArtificial intelligence: What are the risks and benefits?
Watch interviewLooking for speaking opportunities in AI security, generative AI, and machine learning - topics include adversarial attacks on LLMs & conversational AI, model customization & safety alignment, deepfake detection, and enterprise AI applications. Please reach out if you'd like me to present.
Contact
Let's connect
Best way to reach me is email - I read everything.
Open to full-time opportunities starting May 2026.
Happy to chat about AI security, generative AI, conversational AI, or potential collaborations.