โ† Back

Hidden-in-Plain-Text: A Benchmark for Social-Web Indirect Prompt Injection in RAG

AI Agent Security arxiv arXiv:2601.10923 PDF โ†—
indirectwebplaininjectionpromptsocialtextbenchmark
Introduces a benchmark and harness for evaluating web-facing RAG systems under indirect prompt injection and retrieval poisoning attacks with standardized end-to-end evaluation from ingestion to generation.
5~10๋ถ„. ์ œ๋ชฉโ†’์ดˆ๋กโ†’์ธํŠธ๋กœโ†’์„น์…˜ํ—ค๋”โ†’๊ทธ๋ฆผโ†’๊ฒฐ๋ก ๋งŒ.
ํŒ๋‹จ: ์–ด๋–ค ๋ฌธ์ œ๋ฅผ ํ’€๊ณ  / ํ•ต์‹ฌ ์•„์ด๋””์–ด / ๋‚ด ์ž‘์—…๊ณผ ๊ด€๋ จ ์žˆ๋‚˜?
~1์‹œ๊ฐ„. ๊ทธ๋ฆผยทํ‘œ๋ฅผ ๊ผผ๊ผผํžˆ. ์ฆ๋ช…ยท์ˆ˜์‹ ๋””ํ…Œ์ผ์€ ๊ฑด๋„ˆ๋œ€.
์‚ฐ์ถœ๋ฌผ: "์ด๋“ค์ด ๋ญ˜ ํ–ˆ๊ณ  ์™œ ๊ทธ๊ฒŒ ํ†ตํ•˜๋Š”๊ฐ€" ํ•œ ๋ฌธ๋‹จ.
์žฌํ˜„ํ•˜๋“ฏ ์ฝ๊ธฐ. ๊ฐ€์ •์„ ์˜์‹ฌ. ์ง์ ‘ ์ธ์šฉ/๋ฐ˜๋ฐ•ํ•  ๋…ผ๋ฌธ๋งŒ.
๋ Œ์ฆˆ: "๋‚ด ํ”Œ๋ฆฟ์—์„œ ์ธก์ •ํ•˜๋ฉด ์ €์ž๊ฐ€ ๋ชป ํ•œ ๋ฌด์—‡์„ ๋ณด์—ฌ์ค„ ์ˆ˜ ์žˆ๋‚˜?"

Related Papers (10)

Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems
AI Agent Security unread sim 0.43
Defense Against Indirect Prompt Injection via Tool Result Parsing
AI Agent Security unread sim 0.36
Learning to Inject: Automated Prompt Injection via Reinforcement Learning
AI Agent Security unread sim 0.23
PINA: Prompt Injection Attack against Navigation Agents
AI Agent Security unread sim 0.22
SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation
AI Agent Security unread sim 0.20
MARO: Learning Stronger Reasoning from Social Interaction
Multi-Agent unread sim 0.17
Too Helpful to Be Safe: User-Mediated Attacks on Planning and Web-Use Agents
AI Agent Security unread sim 0.17
Aggregation Queries over Unstructured Text: Benchmark and Agentic Method
Memory & RAG unread sim 0.17
Conformity and Social Impact on AI Agents
AI Agent Security unread sim 0.16
Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis
AI Agent Security unread sim 0.16
View in Knowledge Graph โ†’