8 citations · 20 across the 5 of their papers we have counts for
5 papers
LLMs in Web Development: Evaluating LLM-Generated PHP Code Unveiling Vulnerabilities and Limitations
Rebeka Tóth, Tamas Bisztray, László Erdodi
This study evaluates the security of web application code generated by Large Language Models, analyzing 2,500 GPT-4 generated PHP websites. These were deployed in Docker containers…
Simulating SQL Injection Vulnerability Exploitation Using Q-Learning Reinforcement Learning Agents
Laszlo Erdodi, Åvald Åslaugson Sommervoll, Fabio Massimo Zennaro
In this paper, we propose a formalization of the process of exploitation of SQL injection vulnerabilities. We consider a simplification of the dynamics of SQL injection attacks by…
Stack-based Buffer Overflow Detection using Recurrent Neural Networks
William Arild Dahl, Laszlo Erdodi, Fabio Massimo Zennaro
Detecting vulnerabilities in software is a critical challenge in the development and deployment of applications. One of the most known and dangerous vulnerabilities is stack-based…
The Agent Web Model -- Modelling web hacking for reinforcement learning
Laszlo Erdodi, Fabio Massimo Zennaro
Website hacking is a frequent attack type used by malicious actors to obtain confidential information, modify the integrity of web pages or make websites unavailable. The tools use…
Modeling Penetration Testing with Reinforcement Learning Using Capture-the-Flag Challenges: Trade-offs between Model-free Learning and A Priori Knowledge
Fabio Massimo Zennaro, Laszlo Erdodi
Penetration testing is a security exercise aimed at assessing the security of a system by simulating attacks against it. So far, penetration testing has been carried out mainly by…