analiza aiqbench
This paper examines a concrete risk of putting LLMs in charge of telecom network control: prompt injection can steer resource allocation and slicing decisions. Its proposed layer checks consistency across the full path from operator intent to final action, and the reported drop in attack success (0.92 to 0.29) comes from a single testbed (OAIC) with a roughly 27 ms latency cost. Readers should treat these as early, platform-specific results, but the core point, that LLM agents in critical control loops need end-to-end verification rather than only runtime filters, applies broadly.
CLIC: Closed-Loop Intent Consistency for Securing LLM-Driven Control in Open RAN
arXiv:2610.40744v1 Announce Type: cross Abstract: With the progressive capabilities of large language models (LLMs), researchers are finding ways to integrate them into the control loops of Open Radio Access Network (O-RAN) to enable slicing and resource management through user intents. However, integration of LLMs in the O-RAN control loop via the RAN Intelligent Controller (RIC) makes the system vulnerable to \textit{runtime prompt injection threats}, which manipulate control decisions without violating interface authentication, and \textit{residual virtual prompt injection (VPI)} attacks that plant trigger mechanisms to silently steer the behaviour during fine-tuning. Existing studies address only the runtime threat and do not enforce consistency across the full control path, i.e. from the certified A1 intent, through the multi-step LLM trajectory, to the final E2 action. 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.
Abstract:With the progressive capabilities of large language models (LLMs), researchers are finding ways to integrate them into the control loops of Open Radio Access Network (O-RAN) to enable slicing and resource management through user intents. However, integration of LLMs in the O-RAN control loop via the RAN Intelligent Controller (RIC) makes the system vulnerable to \textit{runtime prompt injection threats}, which manipulate control decisions without violating interface authentication, and \textit{residual virtual prompt injection (VPI)} attacks that plant trigger mechanisms to silently steer the behaviour during fine-tuning. Existing studies address only the runtime threat and do not enforce consistency across the full control path, i.e. from the certified A1 intent, through the multi-step LLM trajectory, to the final E2 action. 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.
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI)
arXiv:2610.40744 [cs.CR]
(or arXiv:2610.40744v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2610.40744 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 323 cuvinte