Cybersecurity + AI Researcher

Privacy, security, and trustworthy AI for real-world systems.

I am Anindya Maiti, Assistant Professor of Computer Science and Data Science at the University of Oklahoma, where I direct SecretLab.

My research combines cybersecurity, AI/ML, and systems thinking to uncover practical vulnerabilities and build defensible solutions across connected devices, software ecosystems, and human-centered digital infrastructure.

Anindya Maiti portrait

Focus Areas

Cybersecurity Research Applied AI Security Privacy and Compliance Threat Modeling Dataset Valuation AI Ethics Censorship Circumvention

Bio

Security researcher by profession and technology builder by practice. I focus on attack measurement, privacy risk discovery, and resilient defenses across web, network, and AI-enabled systems. I build practical research systems and datasets spanning censorship resistance, software supply-chain security, and human-centered cybersecurity. I am also founder of GeoSNO and co-inventor of CryptoMiner.

When away from computers, I would brew coffee, eat ramen, fix my beater car, and catch Pokémon in national parks.

Current Roles

Director, SecretLab at the University of Oklahoma.

Assistant Professor, Computer Science and Data Science.

Community Outreach Director, ScooterLab.

Research collaboration across cybersecurity, AI, and digital trust.

Active in academia-industry projects with measurable security outcomes.

Research

Publications

NinjaDoH: A Censorship-Resistant Moving Target DoH Server Using Hyperscalers and IPNS MADWeb 2026 (to appear) · Pre-Print
Prompt and Circumstances: Evaluating the Efficacy of Human Prompt Inference in AI-Generated Art EvoMUSART 2026 (to appear) · Pre-Print
We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs USENIX Security 2025 · Distinguished Paper Award · Paper · Code+Dataset
A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks IJCAI 2025 · Paper
From Big Data to Valued Data: A Dataset Value Taxonomy for AI-Native Empirical Research AAAI/ACM AIES 2025 · Paper
Why You've Got Mail: Evaluating Inbox Privacy Implications of Email Marketing Practices in Online Apps and Services CODASPY 2025 · Paper · Code+Dataset
EtherBee: A Global Dataset of Ethereum Node Performance Measurements Coupled with Honeypot Interactions and Full Network Sessions ICBC 2025 · Paper · Code+Dataset
Initial Evidence of Elevated Reconnaissance Attacks Against Nodes in P2P Overlay Networks BSCI 2025 · Paper
MagnetDB: A Longitudinal Torrent Discovery Dataset with IMDb-Matched Movies and TV Shows ICWSM 2025 · Paper · Code+Dataset
Spiking Neural Networks in Vertical Federated Learning: Performance Trade-offs NOMS 2025 · Paper
De-anonymizing VR Avatars using Non-VR Motion Side-channels WiSec 2024 · Paper

Full publication list: Google Scholar

Office

Devon Energy Hall 460

110 W Boyd St, Norman, Oklahoma 73019, USA

Office Hours: Wednesdays 11:00 AM to 12:00 PM CST/CDT

Secure File Drop: maiti.info/filedrop