# CORA: Teacher-Guided Causal O-RAN Adaptation for Jamming Detection

DevFeed: [CORA: Teacher-Guided Causal O-RAN Adaptation for Jamming Detection](<https://devfeed.tech/articles/cora-teacher-guided-causal-o-ran-adaptation-for-jamming-detection-116931.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.04330>)

Author: Sneihil Gopal, Richard A. Rouil

Published: 2026-11-04T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [network security](<https://devfeed.tech/topics/network-security.md>), [5G](<https://devfeed.tech/topics/5g.md>), [streaming data analytics](<https://devfeed.tech/topics/streaming-data-analytics.md>), [Self-supervised learning](<https://devfeed.tech/topics/self-supervised-learning.md>), [outlier-detection](<https://devfeed.tech/topics/outlier-detection.md>)

Tags: [5g](<https://devfeed.tech/tags/5g.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [alarm](<https://devfeed.tech/tags/alarm.md>), [all](<https://devfeed.tech/tags/all.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attack](<https://devfeed.tech/tags/attack.md>), [best](<https://devfeed.tech/tags/best.md>), [but](<https://devfeed.tech/tags/but.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [context](<https://devfeed.tech/tags/context.md>), [control](<https://devfeed.tech/tags/control.md>), [controller](<https://devfeed.tech/tags/controller.md>), [covers](<https://devfeed.tech/tags/covers.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [deep](<https://devfeed.tech/tags/deep.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [design](<https://devfeed.tech/tags/design.md>), [detection](<https://devfeed.tech/tags/detection.md>), [event](<https://devfeed.tech/tags/event.md>)

## AI overview

CORA transfers a retrospective KPI detector's hindsight to a causal detector for streaming O-RAN jamming detection. Offline, a teacher scores unlabeled historical logs to provide a recall-weighted reward while a masked reinforcement-learning controller adapts detector sensitivity, persistence, and grace. At deployment, the teacher is removed; the frozen controller acts causally without attack labels or target-specific calibration. In leave-one-out transfer across ten 5G O-RAN testbed configurations, PPO raised mean recall from 0.687 to 0.771 over a fixed default detector on all ten. DQN achieved an F2-score comparable to the best teacher-selected static configuration with 61% fewer false alarms. Removing the teacher reduced recall on every configuration.

## Source excerpt

arXiv:2611.04330v1 Announce Type: cross Abstract: In mission-critical networks, a missed jamming event is costlier than a false alarm, so detectors should favor recall, operate causally, and work without labeled attack data. Retrospective Key Performance Indicator (KPI) detectors meet the label-free requirement but rely on future context and cannot run in streaming operation. We present CORA, a teacher-guided reinforcement learning (RL) framework that transfers the hindsight of a retrospective detector to a causal one without labels during training or deployment. Offline, a retrospective KPI detector evaluated on unlabeled historical logs defines a recall-weighted reward for a masked controller that adapts the sensitivity, persistence, and grace of a causal KPI detector. At deployment, the teacher is removed and the frozen controller acts causally, with no ground-truth labels and no target-specific calibration. The design maps onto offline training in the Non-Real-Time RIC and causal control in the Near-Real-Time RIC of an Open Radio Access Network (O-RAN). Under leave-one-out transfer across ten 5G O-RAN testbed configurations, CORA reaches recall-oriented operating points on the deployable frontier that none of the evaluated baselines covers. A Proximal Policy Optimization (PPO) controller raises mean recall from 0.687 to 0.771 over a fixed default detector on all ten configurations, while a Deep Q-Network (DQN) achieves a comparable F2-score to the best teacher-selected static configuration, with 61% fewer false alarms. Removing the teacher lowers recall on every configuration.