Today I’ll talk about a technical topic related to the composition of LLMs. Are LLMs only data (weights) or do they contain code? If they contain code, can this code contain malware? And one additional question, if they have code, can they have vulnerabilities like heap overflows? In this episode I analyze what we exactly download when we download a model with Ollama or with the Hugging Face API.

References

• https://ollama.com/
• https://huggingface.co
• https://docs.vllm.ai/en/latest/
• https://github.com/kserve/kserve
• https://huggingface.co/docs/transformers/en/index
• https://ollama.com/library
• https://huggingface.co/ibm-granite/granite-3.1-2b-instruct
• https://huggingface.co/microsoft/Phi-3.5-mini-instruct/tree/main
• https://www.usenix.org/conference/usenixsecurity23/presentation/christou
• https://arxiv.org/abs/2307.05642