LeakDojo benchmarks reveal that RAG leakage is approximated by the product of query generation and adversarial instruction effects, with higher risk tied to LLM instruction-following ability and RAG faithfulness improvements.
Example output: Query 1 Query 2 Query 3
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
LeakDojo: Decoding the Leakage Threats of RAG Systems
LeakDojo benchmarks reveal that RAG leakage is approximated by the product of query generation and adversarial instruction effects, with higher risk tied to LLM instruction-following ability and RAG faithfulness improvements.