DiscourseFlip is a graph-guided attack allocating limited poisoning budget to induce targeted opinion shifts over semantic query networks in black-box RAG.
Unic-rag: Universal knowledge corruption attacks to retrieval-augmented generation,
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
ImageAuditor is the first MIA for IRAG that achieves over 80% AUROC with four queries by using reward-guided policy optimization for cross-modal retrieval and task-specific prompting for signal extraction.
Routing Hijacking forges client profiles to misroute queries in FedRAG, causing failures like incorrect answers and hallucinations, with a trust-aware post-routing defense proposed to mitigate it.
Injecting a few vectors near the embedding-space centroid can make them appear in top-k results for up to 94.4% of queries via centrality-driven hubness.
ARENA creates anonymized SOC telemetry artifacts that reveal a measurable privacy-utility boundary when used both as training material for MITRE-mapped challenges and as a substrate to detect non-compliant LLM defender actions.
citing papers explorer
-
DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation
DiscourseFlip is a graph-guided attack allocating limited poisoning budget to induce targeted opinion shifts over semantic query networks in black-box RAG.
-
ImageAuditor: Membership Inference Attack against Image-based Retrieval-Augmented Generation
ImageAuditor is the first MIA for IRAG that achieves over 80% AUROC with four queries by using reward-guided policy optimization for cross-modal retrieval and task-specific prompting for signal extraction.
-
A Wolf in Sheep's Clothing: Targeted Routing Hijacking in Federated RAG
Routing Hijacking forges client profiles to misroute queries in FedRAG, causing failures like incorrect answers and hallucinations, with a trust-aware post-routing defense proposed to mitigate it.
-
Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects
Injecting a few vectors near the embedding-space centroid can make them appear in top-k results for up to 94.4% of queries via centrality-driven hubness.
-
ARENA: An Architecture for Measuring the Transferability of Autonomous Cyber Defense
ARENA creates anonymized SOC telemetry artifacts that reveal a measurable privacy-utility boundary when used both as training material for MITRE-mapped challenges and as a substrate to detect non-compliant LLM defender actions.