LivePI benchmark shows indirect prompt injection attack success rates of 10.7% to 29.6% across five AI models in live test environments covering seven input surfaces and multiple malicious goals.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injectio
LivePI benchmark shows indirect prompt injection attack success rates of 10.7% to 29.6% across five AI models in live test environments covering seven input surfaces and multiple malicious goals.