ADAPTIVE ECCM FOR MITIGATING SMART JAMMERS Shashwat Jain * , Kunal Pattanayak * , Vikram Krishnamurthy * and Christopher Berry † * Electrical and Computer Engineering, Cornell University, USA † Lockheed Martin Advanced Technology Laboratories, USA. ABSTRACT This paper considers adaptive radar electronic counter-counter measures (ECCM) to mitigate ECM by an adversarial jam- mer. Our ECCM approach models the jammer-radar inter- action as a Principal Agent Problem (PAP), a popular eco- nomics framework for interaction between two entities with an information imbalance. In our setup, the radar does not know the jammer’s utility. Instead, the radar learns the jam- mer’s utility adaptively over time using inverse reinforcement learning. The radar’s adaptive ECCM objective is two-fold (1) maximize its utility by solving the PAP, and (2) estimate the jammer’s utility by observing its response. Our adaptive ECCM scheme uses deep ideas from revealed preference in micro-economics and principal agent problem in contract the- ory. Our numerical results show that, over time, our adaptive ECCM both identifies and mitigates the jammer’s utility. Index Terms— Adaptive Electronic counter countermea- sures, Afriat’s theorem, Bayesian Target Tracker, Principal Agent Problem, Information Asymmetry, Electronic Warfare 1. INTRODUCTION Electronic Countermeasures (ECM) are widely used by jam- mers to degrade radar’s measurement accuracy in a shared spectrum environment. To mitigate the impact of ECM, mod- ern radars implement Electronic Counter-Countermeasures (ECCM). We consider a target-tracking cognitive radar that maximizes its signal-to-noise ratio (SNR) and is also aware of an adversarial jammer trying to mitigate the radar’s per- formance. At the start of the radar-jammer interaction, the radar has zero information about the jammer’s strategy. The radar learns the jammer’s ECM strategy over time via re- peated radar-jammer interactions while ensuring its measure- ment accuracy lies over a specified threshold - we term this as * V. Krishnamurthy, K. Pattanayak and S. Jain are with the School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, 14853 USA. e-mail: vikramk@cornell.edu, kp487@cornell.edu, sj474@cornell.edu. † C. Berry is with Lockheed Martin Advanced Technology Laboratories, Cherry Hill, NJ, 08002 USA. e-mail: christo- pher.m.berry@lmco.com. This research was supported in part by a re- search contract from Lockheed Martin and the Army Research Office grant W911NF-21-1-0093. adaptive ECCM. A list of standard ECM and ECCM strate- gies are summarized in [1] and [2]. This paper formulates the radar’s ECCM objective as a Principle Agent Problem (PAP), wherein the radar gradually learns the jammer’s objective using Inverse Reinforcement Learning (IRL). We assume the radar possesses IRL capa- bility and can learn the jammer’s utility, while the jammer is a naive agent - it only maximizes its utility. Reconstruct- ing agent preferences from a finite time series dataset is the central theme of revealed preference in micro-economics [3], [4]. In the radar context, the radar uses the celebrated result of Afriat’s theorem [3] to estimate the jammer’s utility over time. This imbalance of information is termed as information asymmetry in literature widely studied in micro-economics [5][6]. The Principal Agent Problem (PAP) is a well-known framework that mitigates information asymmetry. The PAP [7] has been studied extensively in micro-economics for ap- propriate contract formulation between two entities in labor contracts [8], insurance market [9][10], and differential pri- vacy [11] in machine learning. Our choice of PAP is motivated by its flexibility to ac- commodate additional constraints on the information of the radar and the jammer. Such capabilities have been capitalized upon in prior ECCM literature [12]. However, our work gen- eralizes [12] in that the radar now has to learn the jammer’s utility over time using IRL. Similar approaches for mitigat- ing information asymmetry exist in literature, for example, in consumer economics [13] where the seller maximizes its profit by solving a leader-follower problem. In [14], the seller maximizes his utility by modelling his interaction with the consumer as a Stackelberg game. 2. RADAR-JAMMER INTERACTION FOR ADAPTIVE ECCM In this section, we formulate the radar, jammer and target in- teraction as shown in Fig. 1. The radar and jammer inter- act while the target evolves independently. The main idea is that the radar exploits this interaction to mitigate the effect of ECM by using ECCM. For simplicity we only consider a sin- gle target. We formulate the scenario in two timescales. Let n ∈{0, 1, 2,...} and k ∈{0, 1, 2,...}, denote the time index for fast and slow timescale, respectively. In fast timescale, the ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | 978-1-7281-6327-7/23/$31.00 ©2023 IEEE | DOI: 10.1109/ICASSP49357.2023.10095625