Xiao-Nan Ren

Results show that apparent attack winners depend on text-quality constraints, attack generality, and capability assumptions, and that apparent attack winners depend on text-quality constraints, attack generality, and capability assumptions.

This paper introduces InceptionRAG, a stealthy attack mechanism that subverts the standard attack paradigm of RAG, and shows superior evasion capabilities, effectively bypassing established defenses that mitigate traditional single-document injections.