Synthesis Smuggling: Maliciously Hiding Inferred Personal Attributes in LLM Outputs
Title card · GETSECURE.ai
We propose Synthesis Smuggling, a novel threat model in which an adversarial LLM infers sensitive information about a user from routine assistance-seeking interactions an
Excerpt from arXiv AI
GETSECURE.ai hasn't published its own summary of this story yet. The complete report is at arXiv AI:
