No article text was recorded for this version.
sandboxed code execution
Version 1 of 1301 papers412 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Leveraging Static Analysis for Feedback-Driven Security Patching in LLM-Generated Code
- Blog: How Well Do Large Language Models Serve as End-to-End Secure Code Agents for Python?
- Blog: Is your prompt poisoning code? Defect induction rates and security mitigation strategies
- Blog: Instruction Tuning for Secure Code Generation
- Blog: Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study
- Blog: Do Users Write More Insecure Code with AI Assistants?
- Blog: Does Teaming-Up LLMs Improve Secure Code Generation? A Comprehensive Evaluation with Multi-LLMSecCodeEval
- Blog: An Investigation into Misuse of Java Security APIs by Large Language Models
- Blog: An Empirical Cybersecurity Evaluation of GitHub Copilot's Code Contributions
- Blog: Instruction Tuning for Secure Code Generation
- Blog: CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models
- Blog: Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
- Blog: Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey
- Blog: Amazon Nova AI Challenge - Trusted AI: Advancing secure, AI-assisted software development
- Blog: Towards Machine-Generated Code for the Resolution of User Intentions
- Blog: Is Your AI-Generated Code Really Safe? Evaluating Large Language Models on Secure Code Generation with CodeSecEval
- Blog: Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation
- Blog: SWE-chat: Coding Agent Interactions From Real Users in the Wild
- Blog: Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model
- Blog: Security Implications of Large Language Model Code Assistants: A User Study
- Blog: CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain
- Blog: Systematically Finding Security Vulnerabilities in Black-Box Code Generation Models
- Blog: StreamLink: Large-Language-Model Driven Distributed Data Engineering System
- Blog: Preface to the Special Issue on Software Quality Assurance in the Era of Large Language Models
- Blog: LLM4AD: A Platform for Algorithm Design with Large Language Model
- Blog: SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code
- Blog: When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in LLM Coding Agents
- Blog: Every Software as an Agent: Blueprint and Case Study
- Blog: CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
- Blog: Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities
- Blog: Benchmarking Correctness and Security in Multi-Turn Code Generation
- Blog: ToolBridge: An Open-Source Dataset to Equip LLMs with External Tool Capabilities
- Blog: Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences
- Blog: InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
- Blog: Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants
- Blog: A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly
- Blog: INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
- Blog: Large Language Models for Code: Security Hardening and Adversarial Testing
- Blog: Understanding Security Risks of AI Agents' Dependency Updates
- Blog: Instruction Tuning for Secure Code Generation
- Blog: Practices and Challenges of Using GitHub Copilot: An Empirical Study
- Blog: CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models
- Blog: LEVER: Learning to Verify Language-to-Code Generation with Execution
- Blog: SmartCoder-R1: Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization
- Blog: A Design and Implementation of Programming Examination Platform with Compilation Feature
- Blog: Mirror: A Natural Language Interface for Data Querying, Summarization, and Visualization
- Blog: Seattle: a platform for educational cloud computing
- Blog: Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks
- Blog: Can You Really Trust Code Copilot? Evaluating Large Language Models from a Code Security Perspective
- Blog: Case2Code: Scalable Synthetic Data for Code Generation
- Blog: Comparative Analysis of Large Language Models for the Machine-Assisted Resolution of User Intentions
- Blog: KernelBot: A Competition Platform for Writing Heterogeneous GPU Code
- Blog: SecureAgentBench: Benchmarking Secure Code Generation under Realistic Vulnerability Scenarios
- Blog: SecCodePLT: A Unified Platform for Evaluating the Security of Code GenAI
- Blog: Discrete prompt optimization using genetic algorithm for secure Python code generation
- Blog: Support for the File System Security Requirements of Computational E-Mail Systems
- Blog: Demo: SGCode: A Flexible Prompt-Optimizing System for Secure Generation of Code
- Blog: Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software
- Blog: When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
- Blog: SecCoder: Towards Generalizable and Robust Secure Code Generation
Showing 60 of 301 papers.
History & citation
Current · Permanent link
- Activating Latent Security Knowledge via Vulnerability-Aware Prompting merged into this direction (55% overlap)
- Autonomous Agents with Executable Code Actions merged into this direction (58% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_sandboxed_code_execution_aad5f492,
title = {sandboxed code execution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sandboxed-code-execution/rdr_aad5f492648b4e0db65ee1bae84d45c3},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_sandboxed_code_execution_aad5f492_v1,
title = {sandboxed code execution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sandboxed-code-execution/rdr_aad5f492648b4e0db65ee1bae84d45c3/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}