2 papers
cs.CR2026
KidnapRAG: A Black-Box Attack for Hijacking Reasoning in Agentic Retrieval-Augmented Generation Systems
Chanwoo Choi, Euntae Kim, Kyuho Lee +6
Retrieval-Augmented Generation (RAG) systems are vulnerable to poisoning attacks that inject malicious documents into the retrieval process to manipulate model outputs. Recent Agen…
cs.CL2026
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
Dasol Choi, Eugenia Kim, Jaewon Noh +14
Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's a…