The Language of Security: How Prompt Syntax Shapes Secure Code Generation in Open LLMs

arXiv:2607.15937 · cs.CR, cs.SE · Submitted 2026-07-17 · Read on arXiv

Matteo Cicalese, Antonio Della Porta, Stefano Lambiase, Emanuele Iannone, Torge Hinrichs, Riccardo Scandariato, Fabio Palomba

cs.CR, cs.SE

Submitted: 2026-07-17

Comments: Accepted at ICSME 2026

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

Terminology

• Prompt Engineering — 5× in this paper · explained in 4 episodes
• Scaffolding — 5× in this paper · explained in 3 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Analyzer — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifiability — 1× in this paper · explained in 2 episodes

Sources

• Evaluating Large Language Models Trained on Code
• Code Roulette: How Prompt Variability Affects LLM Code Generation
• GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
• On the Opportunities and Risks of Foundation Models
• EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
• Selective Prompt Anchoring for Code Generation
• An Exploratory Study on Fine-Tuning Large Language Models for Secure Code Generation

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