Aravind Cheruvu

Graduate Student (Ph.D.)

Department of CS, Virginia Tech

acheruvu@vt.edu

Google Scholar

GitHub

Resume

About Me

I am a graduate student in the Computer Science department at Virginia Tech, advised by Dr. Bimal Viswanath. 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 expertise lies in conversational AI systems, particularly chatbots. I am currently investigating and mitigating toxicity in chatbots and working on model customization pipelines. My research explores attacks and defenses using state-of-the-art Large Language Models (LLMs). Additionally, I have experience in the Computer Vision (CV) domain, working on deepfakes, GANs, and diffusion models. Beyond my research, I 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.

PS: I am actively seeking research internship roles in generative AI and security for Summer 2025. If you are interested, please drop me an email.

Latest News

Publications

Ph.D. Publications
  • A First Look at Toxicity Injection Attacks on Open-domain Chatbots
    Aravind Cheruvu, Connor Weeks, Sifat Muhammad Abdullah, Shravya Kanchi, Daphne Yao, and Bimal Viswanath
    ACSAC 2023, Austin, Texas, December 2023.
    PDF Code and dataset Video

  • An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape
    Sifat Muhammad Abdullah, Aravind Cheruvu, Shravya Kanchi, Taejoong Chung, Peng Gao, Murtuza Jadliwala and Bimal Viswanath
    IEEE S&P (Oakland) 2024, San Francisco, CA, May 2024.
    PDF Code and dataset

Prior Publications
  • Using normal distribution to retrieve temporal associations by Euclidean distance
    Aravind Cheruvu, V Radhakrishna, N Rajasekhar
    2017 International Conference on Engineering & MIS (ICEMIS)

  • Estimating temporal pattern bounds using negative support computations
    Aravind Cheruvu, V Radhakrishna
    International Conference on Engineering & MIS 2016

  • VRKSHA: A novel multi-tree based sequential approach for seasonal pattern mining
    Shadi Aljawarneh, V Radhakrishna, Aravind Cheruvu
    International Conference on Engineering & MIS 2018

  • Feature clustering for anomaly detection using improved fuzzy membership function
    Gunupudi Rajesh Kumar, Nimmala Mangathayaru, Gugulothu Narsimha, Aravind Cheruvu
    International Conference on Engineering & MIS 2018

  • A dissimilarity measure for mining similar temporal association patterns
    Vangipuram Radhakrishna, PV Kumar, Vinjamuri Janaki, Aravind Cheruvu
    IADIS International Journal on Computer Science and Information Systems 2017

For more publication list refer to my Google Scholar link.
Patents
  • Indian Patent No. 387074 - System and Method for Diagnosis of Diseases From Medical Images
    Filing date: 05/14/2020
    A novel machine learning implementation of Covid-19 detection system using Chest X-rays.

  • Indian Patent No. 397728 - System and Method to Generate Time-Profiled Temporal Pattern Tree
    Filing date: 12/03/2018
    A novel Temporal Tree structure to find the Temporal Association rules.

Education

  • Virginia Polytechnic Institute And State University (Virginia Tech)

    Ph.D. in computer Science (M.S. along the way)

    Aug 2021 - Present

    CGPA: 3.75 *

    Graduate courses: Data 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

  • Jawaharlal Nehru Technological University (VNR VJIET)

    Bachelors in Information Technology

    Sep 2012 - May 2016

    CGPA: 8.51/10.0 "Gold Medal for best outgoing student from the Department of I.T."

Achievements

  • I have successfully passed my Ph.D. Qualifier exam with a perfect score. I am now a Ph.D. candidate.
  • Received "Pratt Fellowship" from the Department of Computer Science.
  • Awarded with CCI SWVA Cyber Innovation Scholarship from Commonwealth Cyber Initiative (CCI) for FY 23 AND 24.
  • Received “Best Poster award at CCI researcher showcase” - Future cybersecurity leaders showcase research

Skills

  • NLP-GenAI expertise: LLMS (LLAMA2, FALCON, Vicuna, FLAN, OPT), Model customization (standard fine-tuning, LoRA fine-tuning), Safety alignment (Supervised fine-tuning, Direct preference optimization), Adversarial attacks
  • CV-GenAI expertise: Stable Diffusion, StyleGAN, Deepfake generation and detection, Adversarial attacks
  • Machine Learning libraries: Huggingface Transformers,Tokenizers, Parameter-Efficient Fine-Tuning (PEFT), Accelerate, DeepSpeed, PyTorch, Numpy, Scikit-Learn, Pandas, Transformer Reinforcement Learning (TRL)
  • Programming Languages: Python, Java, C, C++, HTML/CSS
  • Developer Tools: SQL Developer, VS Code, Eclipse, Netbeans, Android Studio, Weka
  • Technologies/Frameworks: Linux, GitHub, Java Swing, AWT
  • Oracle Tools/Software: Oracle SQL, Oracle HCM Cloud HR And Payroll Module, Payroll Parallel/Reconciliation Tool (Data Analysis), HCM Extracts, Oracle BI Reports, Fast Formulas

Work Experience

  • Deloitte Consulting

    Senior Consultant

    Jun 2021 - Jul 2021

    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.

    Consultant

    Sep 2018 - Jun 2021

    Payroll Reconciliation: Led planning and execution of Payroll Compare cycles for multiple clients to perform trend analysis of \$MM employee payrolls to 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 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 to extensively perform Payroll data analysis.

    Payroll RICEF: Supported Payroll BR100 configurations, Coordinated and executed SIT and UAT testing cycles.

    Business Analyst

    Dec 2016 - Aug 2018

    Technical Developer: Worked as a Technical team member implementing key out-of-box integrations using HCM Extracts to Kronos and Benefits systems, BI Publisher Reports using eText and RTF templates and developed Payroll Fast Formulas.

  • Tata Consultancy Services

    Assistant System Engineer - Trainee

    Jun 2016 - Sep 2016

    Trained in E-Business Suite, Oracle Business Intelligence EE and Oracle Data Integrator tools.