Adam Štorek

Adam Štorek

PhD Student in Computer Science at Columbia University

I am a third-year PhD student advised by Professor Suman Jana. My research advances the robustness and interpretability of code generation models. My recent work examines how these models generate code under adversarial conditions, comprehend long-context code, and exhibit distinct strengths that enable interpretable routing. My goal is to make code AI systems performant and trustworthy for real-world use.

🎓 Education

Columbia University

Columbia University logo
PhD in Computer Science
Advised by Professor Suman Jana
New York, NY
Expected December 2027
Columbia University logo
MS in Computer Science
Security track
New York, NY
December 2022
Columbia University logo
BA in Computer Science
Intelligent Systems track, Magna Cum Laude, Phi Beta Kappa
New York, NY
December 2021

Sciences Po

Sciences Po logo
BA in Economics and Sociology
Mention Cum Laude (Top 10% of the class)
Paris, France
December 2021

💼 Professional Experience

Oracle logo
Oracle
GenAI PhD Research Intern @ Oracle Cloud Infrastructure
Redwood City, CA
Summer & Fall 2025
  • Developed Routesplain, the first interpretable and intervenable LLM router for software-related tasks. Work conducted under Dan Roth; paper under review, patent pending.
Mandiant logo
Mandiant (now Google)
Intern, Reverse Engineering & Malware Analysis @ FLARE
Reston, VA
Summer 2022
  • Reverse-engineered C/C++ and PowerShell malware to support Mandiant's incident responders.
  • Led development of CAPA-scripts, an open-source malware analysis automation tool for identifying malicious capabilities in C#/.NET and Python scripts.
Moderna logo
Moderna
Intern, Data Science & AI
Cambridge, MA
Summer 2020
  • Developed a Bayesian network model for clinical trial enrollment and completion, doubling predictive accuracy over the existing model (WAIC and LOOCV metrics).
  • Built a Python geospatial visualization tool using US Census data to optimize Covid-19 vaccine trial site placement. Presented to the White House and deployed to Moderna's Clinical Dashboard.

📝 Preprints

Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks [paper]

Adam Štorek, Vikas Upadhyay, Marianne Menglin Liu, Daniel W. Peterson, Anshul Mittal, Sujeeth Bharadwaj, Fahad Shah, Dan Roth

Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Reasoning [paper]

Adam Štorek, Mukur Gupta, Samira Hajizadeh, Prashast Srivastava, Suman Jana

XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants [paper]

Adam Štorek, Mukur Gupta, Noopur Bhatt, Aditya Gupta, Janie Kim, Prashast Srivastava, Suman Jana

📄 Publications

CCS 2024 · FOX: Coverage-guided Fuzzing as Online Stochastic Control [paper] [code]

Dongdong She*, Adam Storek*, Yuchong Xie, Seoyoung Kweon, Prashast Srivastava, Suman Jana

ACL 2023 · Unsupervised Selective Rationalization with Noise Injection [paper] [code]

Adam Storek, Melanie Subbiah, Kathleen McKeown

🏆 Awards

🔬 Academic Service

Conference Reviewer
EMNLP 2022

📊 Teaching

Columbia University logo
Columbia University
Teaching Assistant for Malware Analysis & Reverse Engineering
New York, NY
Fall 2025
Columbia University logo
Columbia University
Head Teaching Assistant for Security I
New York, NY
Fall 2024
Columbia University logo
Columbia University
Course Developer with Mike Sikorski
New York, NY
Summer 2023
  • Developed hands-on labs analyzing notable malware (WannaCry, Sony/Destover) for the Malware Analysis & Reverse Engineering class curriculum taught at Columbia University and BlackHat.
Columbia University logo
Columbia University
Head Teaching Assistant for Computer Vision I
New York, NY
Fall 2021
Columbia University logo
Columbia University
Course Developer with Professor Shree Nayar
New York, NY
Summer 2021

🛠️ Technical Skills

Languages: Python, MATLAB, C/C++, Java, Go, Rust, x86, x64

Skills: Cloud Compute (AWS, GCP, Azure), Linux, PyTorch, transformers, vLLM, Pyro, IDA Pro, Ghidra, LLVM