Search papers, labs, and topics across Lattice.
This paper investigates the energy costs associated with implementing mitigation strategies against AI attacks in cellular networks, particularly within the O-RAN framework. It highlights the trade-offs between machine learning model accuracy, robustness against adversarial attacks, and the energy consumption of these defensive techniques. The findings reveal that while effective, current mitigation strategies impose significant computational loads that can compromise energy efficiency, a critical consideration in modern network design.
Effective AI attack mitigation in cellular networks could come at a steep energy cost, challenging the balance between security and efficiency.
The integration of Artificial Intelligence (AI), generally as Machine Learning (ML) algorithms, in all levels and aspects of cellular networks demonstrates the success of data-driven algorithms; for example, the Radio Intelligence Controller (RIC) of the O-RAN paradigm bestows the network with optimised radio resource allocation, load balancing or energy efficiency functions, among others. Nevertheless, this dependency on data opens new security vulnerabilities, as attackers can alter data properties and steer ML models to underperform or degrade. Conversely, the developed mitigation strategies are effective, but they generate a computational load which, in consequence, results in an energy cost generally overlooked, even in the current energy-awareness context. In this work, consumption of a defence technique is characterised, and the challenges raised by the triad of ML accuracy, robustness and energy efficiency are outlined.
