Large-scale analysis of 1.2B URLs identifies 15.3K indirect prompt injection instances in the wild, mostly targeting AI systems with up to 8% compliance in model experiments.
arXiv preprint arXiv:2412.13426 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CR 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.
Large-scale empirical study finds widespread prompt leaking in commercial LLM apps and introduces AREA defense that improves usability while resisting leaks.
citing papers explorer
-
Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives
Large-scale analysis of 1.2B URLs identifies 15.3K indirect prompt injection instances in the wild, mostly targeting AI systems with up to 8% compliance in model experiments.
-
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.
-
Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications
Large-scale empirical study finds widespread prompt leaking in commercial LLM apps and introduces AREA defense that improves usability while resisting leaks.