Squeezing Secrets From Tiny AI: The Risks to Edge Language Models
![The study delineates a threat framework for knowledge extraction from large language models deployed on edge devices, highlighting that despite operating under quantization-such as [latex]INT4[/latex] or [latex]INT8[/latex]-and resource constraints that limit query budgets and introduce noise, strategically designed queries can still elicit substantial behavioral knowledge from these models, contrasting with traditional extraction methods reliant on full-precision teacher models and abundant computational resources.](https://arxiv.org/html/2603.23822v1/x2.png)
As powerful language models shrink to run on devices like phones and IoT sensors, a new study reveals that reducing their size doesn’t necessarily protect the valuable knowledge they contain.





