Pinned Loading
-
Aegis-Gateway
Aegis-Gateway PublicAI security gateway for LLM apps — inspect, filter, and control prompts & responses with built-in guardrails.
Python
-
Prompt-Injection-Detector
Prompt-Injection-Detector PublicLightweight detector for identifying and mitigating prompt injection attacks in LLM workflows.
Python
-
AI-Based-Underhanded-C
AI-Based-Underhanded-C PublicResearch project exploring how AI can generate underhanded or malicious C code, and how such patterns can be detected and mitigated.
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.