Work

Jatmo: Prompt Injection Defense by Task-Specific Finetuning

Year: 2024

Type: conference-paper

Source: Lecture notes in computer science

DOI: 10.1007/978-3-031-70879-4_6

Authors: Julien Piet, Maha Alrashed, Chawin Sitawarin, Sizhe Chen, Zeming Wei, Elizabeth Sun, Basel Alomair, David Wagner

Institutions: University of California, Berkeley, King Abdulaziz City for Science and Technology, Peking University, University of Washington

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, U.S. Department of Homeland Security, Open Philanthropy Project, C3.ai Digital Transformation Institute, King Abdulaziz City for Science and Technology

Awards: AI Institute for Agent-based Cyber Threat Intelligence and Operation, Collaborative Research: SaTC: CORE: Small: Machine Learning for Cybersecurity: Robustness Against Concept Drift

OpenAlex ID: W4402217583

FWCI: 15.67

Cites: 45

Cited by: 70

Related to: 10