Work

Prompt Infection: LLM-to-LLM Prompt Injection within Multi-agent Systems

Year: 2026

Type: conference-paper

Source: Lecture notes in computer science

DOI: 10.1007/978-3-032-16092-8_28

Authors: Donghyun Lee, Mo Tiwari, Brando Miranda

Institutions: University of California, Berkeley, Stanford University

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4403363860

FWCI: 218.5

Cites: 37

Cited by: 227

Related to: 10