Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial
Abay Zhurekbay, Tao Liu, Fan Li
Retrieval-augmented generation (RAG) systems are vulnerable to corpus poisoning: an attacker who inserts a crafted document into the retrieval corpus can steer the underlying large…
cs.CR2026
STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack
Xutao Mao, Liangjie Zhao, Tao Liu +3
Red-teaming Vision-Language Models is essential for identifying vulnerabilities where adversarial image-text inputs trigger toxic outputs. Existing approaches treat image generatio…