LLM-based Code Auditing by Inferring and Evaluating Developer Assumptions

cs.CR, cs.SE

Submitted: 2026-10-11

Updated: 2026-10-11

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Vulnerability Detection with Code Language Models: How Far Are We?
• Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities
• R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
• Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents
• VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs