Intent injection attacks are a new worry for AI-native 6G networks
University of Ottawa and Nokia Bell Labs researchers detail adversarial intent injection against AI-native 6G networks and evaluate two ML detectors on 1,100 crafted intents.
The paper shows attackers with compromised API keys can hide malicious intents—machine-readable JSON requests converted into network policy—among legitimate ones, enabling denial of service, privilege escalation, traffic redirection and backdoors. Two detectors analyzed runs of up to six consecutive requests: a supervised detector caught 75-96% of runs containing malicious requests, while an anomaly-based detector led in three of four attack pacing patterns. The evaluation used 1,100 intents partly built with LLM assistance, and a keyword-based classifier caught only about 10% of malicious intents.
- Compromised API keys let attackers smuggle malicious intents into 6G policy translation
- Consequences include denial of service, privilege escalation, traffic redirection and backdoors
- Supervised detector caught 75-96% of malicious request runs across four pacing patterns
- Both detectors beat single-request analysis, which flagged roughly 50-60% of cases
- Organizations
- University of OttawaNokia Bell Labs
From the original article
2 min read at helpnetsecurity.com
Intent-based networking (IBN) lets operators state the outcome they want and leaves its translation into network policy to software, an approach AI-native 6G designs have moved to the forefront. Researchers at the University of Ottawa and Nokia Bell Labs argue that this abstraction gives attackers new openings, and it tests two machine-learning detectors against one of them.
By Sinisa Markovic · helpnetsecurity.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.