Cover Image

Llama-based source code vulnerability detection: Prompt engineering vs Fine tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ouchebara, Dyna Soumhane, Dupont, Stéphane
Format:	Preprint
Published:	2025
Subjects:	Software Engineering Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM-based Vulnerable Code Augmentation: Generate or Refactor?
by: Ouchebara, Dyna Soumhane, et al.
Published: (2025)

Just another copy and paste? Comparing the security vulnerabilities of ChatGPT generated code and StackOverflow answers
by: Hamer, Sivana, et al.
Published: (2024)

A unit-based symbolic execution method for detecting memory corruption vulnerabilities in executable codes
by: Baradaran, Sara, et al.
Published: (2022)

RefleXGen:The unexamined code is not worth using
by: Wang, Bin, et al.
Published: (2025)

Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models
by: Bruni, Marc, et al.
Published: (2025)

A Qualitative Study on Using ChatGPT for Software Security: Perception vs. Practicality
by: Kholoosi, M. Mehdi, et al.
Published: (2024)

Beyond Classification: Evaluating LLMs for Fine-Grained Automatic Malware Behavior Auditing
by: Zheng, Xinran, et al.
Published: (2025)

TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs
by: Shen, Qingchao, et al.
Published: (2026)

Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
by: Chen, Zhiyang, et al.
Published: (2025)

Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents
by: Crawford, Brian, et al.
Published: (2026)

Retrieval-Augmented Few-Shot Prompting Versus Fine-Tuning for Code Vulnerability Detection
by: Trad, Fouad, et al.
Published: (2025)

Deconstructing Obfuscation: A four-dimensional framework for evaluating Large Language Models assembly code deobfuscation capabilities
by: Tkachenko, Anton, et al.
Published: (2025)

`Do as I say not as I do': A Semi-Automated Approach for Jailbreak Prompt Attack against Multimodal LLMs
by: Chiu, Chun Wai, et al.
Published: (2025)

Natural Language based Specification and Verification
by: Li, Zhaorui, et al.
Published: (2026)

Impact assessment for vulnerabilities in open-source software libraries
by: Plate, Henrik, et al.
Published: (2015)

On the Security Risks of ML-based Malware Detection Systems: A Survey
by: He, Ping, et al.
Published: (2025)

Data and Context Matter: Towards Generalizing AI-based Software Vulnerability Detection
by: Safdar, Rijha, et al.
Published: (2025)

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
by: He, Ping, et al.
Published: (2025)

PentestEval: Benchmarking LLM-based Penetration Testing with Modular and Stage-Level Design
by: Yang, Ruozhao, et al.
Published: (2025)

From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection
by: Li, Youpeng, et al.
Published: (2026)

EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detection
by: Liu, Shigang, et al.
Published: (2024)

Cross-site scripting adversarial attacks based on deep reinforcement learning: Evaluation and extension study
by: Pasini, Samuele, et al.
Published: (2025)

D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning
by: Zou, Muqi, et al.
Published: (2025)

FLAMES: Fine-tuning LLMs to Synthesize Invariants for Smart Contract Security
by: Eshghie, Mojtaba, et al.
Published: (2025)

Arbiter: Detecting Interference in LLM Agent System Prompts
by: Mason, Tony
Published: (2026)

Efficient Detection of Toxic Prompts in Large Language Models
by: Liu, Yi, et al.
Published: (2024)

Prompt Injection attack against LLM-integrated Applications
by: Liu, Yi, et al.
Published: (2023)

Prompting Techniques for Secure Code Generation: A Systematic Investigation
by: Tony, Catherine, et al.
Published: (2024)

AppPoet: Large Language Model based Android malware detection via multi-view prompt engineering
by: Zhao, Wenxiang, et al.
Published: (2024)

Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects
by: Wang, Yuxuan, et al.
Published: (2025)

A Comprehensive Study of Exploitable Patterns in Smart Contracts: From Vulnerability to Defense
by: Ding, Yuchen, et al.
Published: (2025)

QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration
by: Hu, Junze, et al.
Published: (2025)

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
by: Chu, Zhaoyang, et al.
Published: (2025)

Locus: Agentic Predicate Synthesis for Directed Fuzzing
by: Zhu, Jie, et al.
Published: (2025)

Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking
by: Huang, Yifan, et al.
Published: (2025)

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation
by: Zhang, Xiaoyu, et al.
Published: (2025)

Leveraging Large Language Models for Cybersecurity Risk Assessment -- A Case from Forestry Cyber-Physical Systems
by: Gultekin, Fikret Mert, et al.
Published: (2025)

Bridging Semantics & Structure for Software Vulnerability Detection using Hybrid Network Models
by: Gajjar, Jugal, et al.
Published: (2025)

VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization
by: Li, Youpeng, et al.
Published: (2025)

Reflection-Driven Control for Trustworthy Code Agents
by: Wang, Bin, et al.
Published: (2025)