Alex-Hosein
Show HN: InferShield – A Lightweight Orchestration-Layer Attack Detector (POC)
https://github.com/InferShield/infershield
Attacks targeting the orchestration layer (e.g., Kubernetes control planes, cloud APIs) are stealthy and often bypass conventional security mechanisms. These attacks can exploit API misconfigurations, escalate privileges, and compromise infrastructure.We built InferShield, an open-source Proof of Concept, to explore early detection of such threats. InferShield uses session tracking and event...
Show HN: InferShield – open-source security proxy for LLM inference
https://github.com/InferShield/infershield
Hey HN! I'm launching InferShield, an open source security proxy that sits between your application and LLM providers (OpenAI, Anthropic, etc.) to detect and block threats in real-time.I've been talking to CISOs at banks and hospitals who are deploying LLMs without proper security. Their existing tools can't handle LLM-specific threats:- Prompt injection (attackers manipulate LLM behavior, WAFs...