2 papers
cs.CR2026
DICE: Tilting the Odds through Interface Attackson System One Model
Ben Dong, Tianyi Lu, Zhonghao Guo +1
System One models offer typed judgments that applications can turn into decisions. Their answers, however, are conditional on the state and question supplied by surrounding compone…
cs.CR2026
The Claws in Plain Sight: Unauthorized Context Disclosure through LLM Agent Tool Calls
Ben Dong, Zhonghao Guo, Tianyi Lu +1
LLM agents routinely construct tool-call arguments from user profiles, conversation history, retrieved documents, and prior tool results. However, legitimate access to contextual i…