arXiv · cs.AI · Sunder Ali Khowaja, Kapal Dev, Joongheon Kim, Angelos Antonopoulos, Nikolaos Bartzoudis · 10 小时前模型评分37
CLIC：为 Open RAN 中 大语言模型（LLM，Large Language Model） 驱动的控制加装闭环意图一致性防护
CLIC: Closed-Loop Intent Consistency for Securing LLM-Driven Control in Open RAN
导读
研究者提出闭环意图一致性层（CLIC，Closed-Loop Intent Consistency），用于同时防御 Open RAN 中 大语言模型（LLM，Large Language Model） 控制回路的运行时提示注入和残留虚拟提示注入（VPI）攻击。
分类置信度
中 · 待人工复核
- 存在未解决的相邻类别：governance-services，需要人工复核。
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “We propose a closed-loop intent-consistency layer (CLIC) that jointly mitigates both threats.”
- “The proposed CLIC defines a formal consistency score using a small quantized language model, which is deployed as a Non-RT rApp for model-integrity certification along with a Near-RT xApp for runtime enforcement.”
- “We implement CLIC on the OpenAI Cellular (OAIC) platform and evaluate it under domain-adapted JailbreakBench, AdvBench, and VPI workloads.”
- “The experimental results show that the proposed CLIC reduces the attack success rate from 0.92 to 0.29 and residual VPI attacks from 0.37 to 0.04, while improving isolation and fairness at slightly higher latency costs, i.e. approximately 27 ms.”
来源：arXiv · cs.AI · arxiv.org