CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Minbeom, Parmar, Mihir, Wallis, Phillip, Miculicich, Lesly, Jung, Kyomin, Dvijotham, Krishnamurthy Dj, Le, Long T., Pfister, Tomas
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Machine Learning Methodology
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.07918