Cognitive radar hides decision patterns against adversaries effectively
Masking Radar Cognition under Adversarial Surveillance: A Distributional Privacy Framework
Machine Learning
Summary
When smart radars decide how to act, they risk revealing their strategies to enemies who watch them closely. The authors propose ways to keep these radars’ decision methods secret by carefully tweaking their actions so outsiders can’t figure out their goals. They analyze two types of decision styles and show mathematically how well their hiding methods protect radar strategies while still letting the radar work well. Their tests show improved protection compared to older techniques, which is useful for secure communication in future networks and drone coordination.
What this means in practice
- •For network schedulers: Protect resource allocation policies in 6G network slicing for automated driving from privacy attacks.
- •For drone operators: Maintain secret coordination strategies among UAV swarms to prevent adversarial surveillance.
Authors
Sreedevi K, Nandhini K, Anup Aprem, Deepthi P P
Abstract
In this article, we propose an online electronic counter-countermeasure (ECCM) framework designed to conceal the strategic decision-making processes of a cognitive radar (CR) operating under adversarial surveillance. We model the CR under two distinct decision paradigms: a static constrained utility-maximizing behavior and a dynamic expected utility-maximizing behavior. The radar's utility function is modeled via a von Mises--Fisher (vMF) distribution, with the distributional parameter constituting the private information to be protected from adversarial inference. We adopt a distribution privacy framework to conceal this private information and provide formal distribution privacy guarantees for cognition masking. In this work, we develop cognition-hiding algorithms for both static constrained utility maximization (WDPCH-SU), and dynamic expected utility maximization (WDPCH-DU). Through rigorous mathematical analysis, we show that both WDPCH-SU and WDPCH-DU satisfy $ε$-distribution privacy ($ε$-DistP) against inference-based adversarial attacks and present the privacy--performance trade-off bounds, quantifying utility loss (in static setting) and expected utility deviation (in dynamic setting) as functions of $ε$. Numerical results show that WDPCH-SU gives about 15\% improvement in utility loss at maximum privacy compared to the existing methodology while WDPCH-DU achieves a greater reduction in adversarial Fisher information without requiring explicit Fisher information constraints, at a moderate, analytically bounded utility deviation. These results are highly promising in many 6G communication scenarios such as network slicing for automated driving and swarm UAV coordination, where it is essential to keep the resource allocation policy robust against privacy attacks.