Search Results for "ai framework"

PentestGPT is an AI-powered autonomous penetration testing agent designed to perform intelligent, end-to-end security assessments using large language models. Published at USENIX Security 2024, it combines advanced reasoning with an agentic workflow to automate tasks traditionally handled by human pentesters. The platform supports multiple penetration testing categories, including web security, cryptography, reversing, forensics, privilege escalation, and binary exploitation. PentestGPT runs...

RedAmon is an AI-powered red team framework designed to automate offensive cybersecurity operations from reconnaissance to exploitation and post-exploitation. It combines artificial intelligence with traditional penetration testing tools to create a fully autonomous pipeline capable of discovering vulnerabilities and executing security assessments without human intervention.

...The overall architecture is meant to be adaptable, so teams can modify it for other languages, bug classes, and detection systems. Its main value is giving defenders a practical framework for exploring AI-assisted secure code review and remediation.

tirreno is an open-source security framework. tirreno [tir.ˈrɛ.no] helps understand, monitor, and protect your product from threats, fraud, and abuse. While classic cybersecurity focuses on infrastructure and network perimeter, most breaches occur through compromised accounts and application logic abuse that bypasses firewalls, SIEM, WAFs, and other defenses. tirreno detects threats where they actually happen: inside your product. tirreno is a few-dependency, "low-tech" PHP/PostgreSQL...

...Shennina scans a set of input targets for available network services, uses its AI engine to identify recommended exploits for the attacks, and then attempts to test and attack the targets. If the attack succeeds, Shennina proceeds with the post-exploitation phase. The AI engine is initially trained against live targets to learn reliable exploits against remote services. Shennina also supports a "Heuristics" mode for identfying recommended exploits.

Security is a subject of major concern in mobile agents. This project provides a security framework that allows the protection of mobile agents from third parties. A self-protected approach, where the agents themselves manage the process, is used.