REVIEW 8 cited by
AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
read the original abstract
Recent advancements in automatic code generation using large language models (LLMs) have brought us closer to fully automated secure software development. However, existing approaches often rely on a single agent for code generation, which struggles to produce secure, vulnerability-free code. Traditional program synthesis with LLMs has primarily focused on functional correctness, often neglecting critical dynamic security implications that happen during runtime. To address these challenges, we propose AutoSafeCoder, a multi-agent framework that leverages LLM-driven agents for code generation, vulnerability analysis, and security enhancement through continuous collaboration. The framework consists of three agents: a Coding Agent responsible for code generation, a Static Analyzer Agent identifying vulnerabilities, and a Fuzzing Agent performing dynamic testing using a mutation-based fuzzing approach to detect runtime errors. Our contribution focuses on ensuring the safety of multi-agent code generation by integrating dynamic and static testing in an iterative process during code generation by LLM that improves security. Experiments using the SecurityEval dataset demonstrate a 13% reduction in code vulnerabilities compared to baseline LLMs, with no compromise in functionality.
Forward citations
Cited by 8 Pith papers
-
SoK: AI Secure Code Generation: Progress, Pitfalls, and Paths Forward
The paper introduces a three-level framework for AI secure code generation, finds that principle understanding statistically predicts code outcomes, but identifies persistent knowledge-actuation gaps across models and agents.
-
Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
TSP reframes secure code generation as a tree-structured self-play process that supplies dense on-policy signals at vulnerability-prone nodes, yielding higher security pass rates and cross-language generalization than...
-
The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting
Across five coding assistants, authentication code is insecure under basic or generic-secure prompts; single-shot NIST help improves it, but only iterative reprompting approaches defense-in-depth.
-
Code as Agent Harness
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed ...
-
Vibe-Coding: Feedback-Based Automated Verification with no Human Code Inspection, a Feasibility Study
Precise feedback on fine-grained architectural and functional constraint violations enables LLMs to produce valid adaptation managers for collective adaptive systems within a few iterations, unlike coarse metric feedback.
-
A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and Reflection
Vulnsage, a multi-agent framework, generates 34.64% more exploits than prior tools and verified 146 zero-day vulnerabilities in real-world open-source libraries.
-
Critic-Guided Heterogeneous Multi-Agent Reasoning for Reliable Mathematical Problem Solving
A critic-guided heterogeneous multi-agent LLM framework improves GSM8K math reasoning accuracy by up to 13% and enables smaller models to match larger ones via feedback loops.
-
IACDM: Interactive Adversarial Convergence Development Methodology -- A Structured Framework for AI-Assisted Software Development
IACDM is an 8-phase methodology using external verification agents and three pillars to close the verification gap in stochastic LLM-based software development.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.