# SaTC: CORE: Small: Improving the Security of Large Language Model-Assisted Coding

> **NSF 01002627DB NSF RESEARCH & RELATED ACTIVIT** · New Jersey Institute of Technology (NJ) · $450,000

## Abstract

Large Language Model (LLM)-assisted coding, where an LLM automatically generates code based on a developer-specified prompt, is already popular and projected to grow, promising to bolster coding productivity while reducing software development time and effort. LLM-generated code can be insecure for a variety of reasons, for example omitting critical security checks, or containing mistakes that adversaries can exploit. When this insecure code eludes scrutiny and makes its way into production systems, our software infrastructure is at risk. This project advances the state of research and practice in LLM-assisted coding by using program analysis and verification to generate secure code. The project's novelties are to introduce and use guardrails named contexts that define security properties and guide LLMs into producing code that meets such security guarantees. The project's broader significance and importance are empowering programmers to understand the security implications of LLM-assisted coding and in turn write more secure code efficiently, helping fuel economic prosperity and increasing national security.

The project consists of three thrusts. The first thrust uses program analysis to bridge the gap between security properties and LLM code generation via contexts and LLM prompts. The second thrust constructs an iterative LLM-centered code generation approach with criteria designed to improve security in each iteration. The third thrust develops a minimization approach, designed to produce minimal code examples in situations where LLM generation fails, or the LLM cannot converge toward producing secure code. These approaches are usable in a variety of other settings: scenarios where LLM-generated code needs to be rigorously or formally verified, settings where the LLM-produced code must meet certain specifications from the start, and the widely-applicable technique of generating a minimal example when LLM generation fails, so the programmers can easily underst

## Key facts

- **NSF award ID:** 2453331
- **Awardee organization:** New Jersey Institute of Technology (NJ)
- **SAM.gov UEI:** SGBMHQ7VXNH5
- **PI:** Zhihao Yao
- **Primary program:** 01002627DB NSF RESEARCH & RELATED ACTIVIT
- **All programs:** SaTC: Secure and Trustworthy Cyberspace, Artificial Intelligence (AI), Nat Security, Secure Border & Pub Safety, SMALL PROJECT
- **Estimated total:** $450,000
- **Funds obligated:** $450,000
- **Transaction type:** Standard Grant
- **Period:** 05/15/2026 → 04/30/2029

## Primary source

NSF Award Search: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2453331

## Citation

> US National Science Foundation, Award 2453331, SaTC: CORE: Small: Improving the Security of Large Language Model-Assisted Coding. Retrieved via AI Analytics 2026-06-26 from https://api.ai-analytics.org/grant/nsf/2453331. Licensed CC0.

---

*[NSF Awards dataset](/datasets/nsf-awards) · CC0 1.0*