4 min read
SipIt: Extracting System Prompts from Transformer Hidden States
How I achieved 100% token recovery from Mistral-7B hidden states and what it means for AI security
transformers
security
interpretability
Read more
[ Ai-Safety ]
Discover insights, tutorials, and thoughts on technology, homelab, and development.
5 min read
The Hidden State Attack: Why Your LLM's System Prompt Isn't Secret
Responsible disclosure of a class of vulnerabilities that allow system prompt extraction from transformer hidden states
security
llm
transformers
Read more