#AI Security

The project provides a comprehensive collection of baseline strategies for data competitions, aimed at guiding beginners and enthusiasts. The repository focuses on practical and simple solutions, facilitating easy learning and application. Updated competition details and baseline strategies are accessible through related platforms and files, offering broad resources to improve participation and expertise in data challenges.

Explore a wide array of cybersecurity references, tools, and scripts curated by Omar Santos. This extensive repository, comprising over 10,000 resources, supplements books and courses aimed at enhancing the skills of security professionals. Key focus areas include ethical hacking, reverse engineering, threat intelligence, digital forensics, and AI security. Dive into these resources to complement your cybersecurity education. Contributions are encouraged and supported under the MIT License.

Rebuff provides robust protection for AI applications by detecting prompt injection attacks using a multi-layered system including heuristics, LLM-based detection, VectorDB, and canary tokens. This prototype aims to filter malicious inputs, analyze prompts, and prevent future attacks by utilizing past data. It currently offers a JavaScript/TypeScript SDK with plans for a Python SDK and user-defined strategies. The platform supports self-hosting by integrating with providers such as Pinecone and Supabase for database management.