Ibrahim Khalilov
PhD Student in Computer Science @ Johns Hopkins · HCI & Privacy Researcher · Ex-SWE
Passionate about building technology that respects user privacy while advancing human-computer interaction through innovative research and practical solutions.
About Me
I am a PhD student in Computer Science at Johns Hopkins University, where I focus on the intersection of Human-Computer Interaction (HCI), Privacy, and Generative AI. My research explores how we can design and build technology that empowers users while protecting their privacy and autonomy.
My current research interests include privacy-preserving systems, user-centered design for AI applications, and developing frameworks for understanding the risks and benefits of AI agents in everyday computing. I am particularly passionate about creating tools that help users make informed decisions about their digital privacy.
Before pursuing my PhD, I worked as a software engineer at various companies, including Virginia Institute for Spaceflight and Autonomy (VISA), Thrillworks, and Fairly AI. This industry experience has given me a unique perspective on how to bridge the gap between academic research and practical, real-world applications.
I love tackling complex problems that require both technical depth and human-centered thinking. When I'm not researching or coding, I enjoy exploring new technologies and contributing to open-source projects that make privacy and security more accessible to everyone.
Research
Beyond Permissions: Investigating Mobile Personalization with Simulated Personas
Ibrahim Khalilov, Chaoran Chen, Ziang Xiao, Tianshi Li, Toby Jia-Jun Li, Yaxing Yao
This position paper argues for empathy-based design principles in mobile privacy interfaces, proposing a framework for creating more intuitive and effective privacy controls.
The Obvious Invisible Threat: LLM-Powered GUI Agents’ Vulnerability to Fine-Print Injections
Chaoran Chen, Zhiping Zhang, Bingcan Guo, Shang Ma, Ibrahim Khalilov, Simret A Gebreegziabher, Yanfang Ye, Ziang Xiao, Yaxing Yao, Tianshi Li, Toby Jia-Jun Li
An empirical analysis of adversarial threats to LLM-driven GUI agents, revealing their susceptibility to context-based UI attacks and the insufficiency of human oversight as a safeguard.
Projects
Mobile Empathy-Based Sandbox for Privacy Awareness
In ProgressAn innovative mobile application that creates a safe sandbox environment for users to explore and understand privacy implications of their app usage. The system uses empathy-based design principles to make privacy concepts more accessible and actionable.
Key Highlights:
- •Dynamic instrumentation using Frida for real-time app behavior analysis
- •LLM-powered explanations of privacy risks in plain language
- •Interactive sandbox environment for safe privacy exploration
Technologies:
GUI Agent Risk Modeling Framework
In ProgressA comprehensive framework for analyzing and modeling privacy risks associated with LLM-powered GUI agents. This ongoing research project aims to understand how AI agents interact with user interfaces and the potential privacy implications.
Key Highlights:
- •Automated GUI interaction pattern analysis
- •Privacy risk assessment algorithms
- •Framework for evaluating AI agent behavior
Technologies:
Software Engineering Experience
Software Engineer
Thrillworks
Built and shipped multiple mobile and web applications for large corporations including President's Choice (PC Financial, PC Insurance) and Ryobi. Created responsive and accessible websites using modern web technologies.
Key Achievements:
- •Delivered production applications for major corporations like PC Financial
- •Built mobile and responsive apps with Flutter, Gatsby, React, and Tailwind CSS
- •Developed and maintained microservices using NestJS
Technologies Used:
Robotics Software Intern
Virginia Institute for Spaceflight and Autonomy
Developed applications to control robots using WamV ROS network for remote control and feedback reception. Fine-tuned pretrained models for regression and classification tasks, integrating them into control systems.
Key Achievements:
- •Built robot control application using WamV ROS network architecture
- •Fine-tuned ML models for autonomous navigation and control systems
- •Implemented effective communication between ROS nodes and Docker containers
Technologies Used:
Full-stack Developer
Fairly AI
Built scalable web applications for AI-powered fairness assessment tools. Worked with machine learning teams to integrate ML models into production web applications.
Key Achievements:
- •Implemented real-time notification system using WebSockets
- •Built AI risk management dashboard with Material-UI
- •Integrated Firebase authentication and developed user management system
Technologies Used:
Get in Touch
Let's Connect
I'm always interested in discussing research collaborations, potential projects, or just having a conversation about AI, mobile development, and the future of technology. Feel free to reach out!