Benchmarking LLMs agents for vulnerability research​
| | |

Benchmarking LLMs agents for vulnerability research​

ByFuzzingLabs

applied AI for Cybersecurity Benchmarking LLM agents for vulnerability research AI agents appear to be a powerful tool for advancing vulnerability research and securing modern applications. At FuzzingLabs, we decided to take a deep dive into this topic to assess its real-world potential. We conducted experiments by building AI agents using various LLMs, with the…

AI Agents for application security testing
| | |

AI Agents for application security testing

ByFuzzingLabs

applied AI for Cybersecurity AI Agents for application security testing What if AI could autonomously find, trace, and exploit vulnerabilities in code? The rise of AI agents has opened many new possibilities, but one remains underexplored in security: combining static and dynamic testing in a unified, autonomous pipeline. Today’s app-sec solutions typically focus on either…

Android and the mysteries of dial codes ​ – Extracting dial codes by apk reversing
| | | | |

Android and the mysteries of dial codes ​ – Extracting dial codes by apk reversing

ByFuzzingLabs

Android and the mysteries of dial Codes Extracting dial codes by apk reversing Dial Codes, also called USSD or HMI (Human Machine Interface) codes, are typically used by OEM and carrier to implement some menu. While making baseband researches, those hidden menus was very useful. Today, in this small blogpost, I will described the way…

AI-Driven Threat Modeling – LLMs for Automated STRIDE Analysis
| | | |

AI-Driven Threat Modeling – LLMs for Automated STRIDE Analysis

ByFuzzingLabs

AI-Driven Threat Modeling LLMs for Automated STRIDE Analysis Threat modeling has always been about understanding how the components of an application interact, where the boundaries lie, and what could go wrong at each connection. Traditionally, this process has been manual, relying on diagrams and the expertise of security professionals to map out relationships and identify…

EVM Security – Insights from Zer0Con 2025
| | | |

EVM Security – Insights from Zer0Con 2025

ByFuzzingLabs

EVM Security Insights from Zer0Con 2025 At Zer0Con 2025, the FuzzingLabs team, Mathieu Hoste and Bryton Bernard, delivered an engaging and insightful presentation on one of the most critical aspects of Ethereum’s security: the vulnerabilities within the Ethereum Virtual Machine (EVM). In our session, titled “Ethereum’s Achilles’ Heel: Attacking and Fuzzing EVMs for Fun (and…

Linux Hardening – State of Linux Snapshot Fuzzing
| |

Linux Hardening – State of Linux Snapshot Fuzzing

ByFuzzingLabs

Linux Hardening State of Linux Snapshot Fuzzing What is snapshot fuzzing ? Fuzzing is a well-established technique for finding software vulnerabilities, and snapshot fuzzing represents a significant advancement, enhancing efficiency and expanding the scope of testable software. Snapshot fuzzing is particularly valuable in application security where it enables thorough black-box testing of applications, regardless of…

Differential Cryptanalysis 101​ – Exploring Differential Methods in Block Ciphers​
| |

Differential Cryptanalysis 101​ – Exploring Differential Methods in Block Ciphers​

ByFuzzingLabs

Differential Cryptanalysis 101 Exploring Differential Methods in Block Ciphers Cryptanalysis has been playing an essential role in the security of both software and hardware systems for decades and now more than ever. Many knows the essentials of cryptography through school, trainings or self learning, but very few know the ways of cryptanalysis, which is equally…

Introduction to modern memory management
|

Introduction to modern memory management

ByFuzzingLabs

Memory management Introduction to modern memory management The goal of this article is to present the functioning of volatile memory in general on our modern computers. Physical Organization Before discussing volatile memory, it is important to understand the basics of how a computer operates. A PC is composed of several electronic components and peripherals that…

AI hacking, LLM applications, OWASP Top 10, Prompt Injection, Insecure Output Handling, Model Denial of Service, Sensitive Information Disclosure, Model Theft, Best practices, Application protection, LLM attacks
| |

Prompt Injection – AI Hacking & LLM attacks

ByFuzzingLabs

Prompt Injection – AI Hacking & LLM attacks Prompt Injection is a rising concern in the AI realm, especially with models like GPT. In this video, we’ll explore the intricacies of Prompt Injection attacks, demonstrating live on dedicated websites how GPT can be manipulated to potentially leak secret passwords 🛑. More importantly, learn the strategies…

openai chatgpt gpt3.5 gpt4 gpt3 hacking cybersecurity pentesting audit reversing vulnerability research
| |

GPT-4 for Bug Bounty, Audit & Pentesting?? He actually found some 0-days

ByPatrick Ventuzelo

Chatgpt GPT-4 for Bug Bounty, Audit & Pentesting?? He actually found some 0-days I gave some snippets of code (where I already found bugs) to OpenAI GPT-4 and I ask him to find vulnerabilities for me. It’s mind-blowing, it even found some 0 days. You will get access of the complete tutorial with source code, cheat…