Tagged "model-security"
- llama.cpp GGUF Parser Flaws: Critical Integer Overflow Enables Arbitrary Reads in Every Local AI Stack
- Claude Opus 4.7 System Prompt Leaks Raise Local Deployment Questions
- Show HN: Minimal Linux Sandboxes to Manage AI-Generated Code with Ease
- Critical Security Flaw: Hackers Can Exploit Ollama Model Uploads to Leak Sensitive Server Data
- Malicious GGUF Models Could Trigger Remote Code Execution on SGLang Servers
- Hugging Face Moves Safetensors Under PyTorch Foundation