Enhancing O-RAN Security: Evasion Attacks and Robust Defenses for Graph Reinforcement Learning-based Connection Management

TL;DR

This paper explores security threats to ML-based O-RAN connection management, demonstrating effective evasion attacks and proposing robust defenses that improve system coverage despite adversarial noise.

Contribution

It provides a comprehensive threat model for ML-based O-RAN systems, demonstrates practical adversarial attacks, and develops defenses that enhance robustness against physical and jamming attacks.

Findings

Evasion attacks can reduce coverage rates by up to 50%.

Robust training improves coverage rates by 15% under attack.

ML-based connection management outperforms heuristic methods in coverage.

Abstract

Adversarial machine learning, focused on studying various attacks and defenses on machine learning (ML) models, is rapidly gaining importance as ML is increasingly being adopted for optimizing wireless systems such as Open Radio Access Networks (O-RAN). A comprehensive modeling of the security threats and the demonstration of adversarial attacks and defenses on practical AI based O-RAN systems is still in its nascent stages. We begin by conducting threat modeling to pinpoint attack surfaces in O-RAN using an ML-based Connection management application (xApp) as an example. The xApp uses a Graph Neural Network trained using Deep Reinforcement Learning and achieves on average 54% improvement in the coverage rate measured as the 5th percentile user data rates. We then formulate and demonstrate evasion attacks that degrade the coverage rates by as much as 50% through injecting bounded noise at different threat surfaces including the open wireless medium itself. Crucially, we also compare and contrast the effectiveness of such attacks on the ML-based xApp and a non-ML based heuristic. We finally develop and demonstrate robust training-based defenses against the challenging physical/jamming-based attacks and show a 15% improvement in the coverage rates when compared to employing no defense over a range of noise budgets