Intent injection attacks pose new risk to AI-native 6G networks

University of Ottawa and Nokia Bell Labs described an adversarial intent injection attack on intent-based networking, where an attacker with a stolen API key hides malicious instructions among legitimate ones. On a dataset of 1,100 intents, two ML detectors identified 75% to 96% of dangerous request sequences.

• Attack replaces legitimate IBN intents with malicious ones via a compromised API key
• Dataset: 20 base attacks, 9 variants each, 1,100 intents total
• Example-based detector caught 75–96% of dangerous request sequences
• Anomaly detector missed about a third of fixed-rate attacks