A systematic learning method for optimal jamming

Jamming is an ongoing threat that plagues wireless communications in contested areas. Unfortunately, jamming complexity and sophistication will continue to increase over time. The traditional approach to addressing the jamming threat is to harden radios, such that they sacrifice communications performance for more advanced jamming protection. To provide an escape from this trend, we investigate the previously unexplored area of jammer exploitation.This dissertation develops the concept of antifragile communications, defined as the capability for a communications system to improve in performance due to a system stressor or harsh condition. Antifragility refers to systems that increase in capability, resilience, or robustness as a result of disorder (e.g., chaos, uncertainty, stress). An antifragile system is fundamentally different from one that is resilient (i.e., able to recover from failure) and robust (i.e., able to resist failure). We apply the concept of antifragility to wireless communications through several novel strategies that all involve exploiting a communications jammer. These strategies can provide an increase in throughput, efficiency, connectivity, or covertness, as a result of the jamming attack itself. Through analysis and simulation, we show that an antifragile gain is possible under a wide array of electronic warfare scenarios. Throughout this dissertation we provide guidelines for realizing these antifragile waveforms. Other major contributions of this dissertation include the development of a communications jamming taxonomy, feasibility study of reactive jamming in a SATCOM-type scenario, and a reinforcement learning-based reactive jamming mitigation strategy, for times when an antifragile approach is not practical.Most of the jammer exploitation strategies described in this dissertation fall under the category of jammer piggybacking, meaning the communications system turns the jammer into an unwitting relay. We study this jammer piggybacking approach under a variety of reactive jamming behaviors, with emphasis on the sense-and-transmit type. One piggybacking approach involves transmitting using a specialized frequency-shift keying (FSK) waveform, tailored to exploit a jammer that channelizes a block of spectrum and selectively jams active subchannels. To aid in analysis, we introduce a generalized model for reactive jamming, applicable to both repeater-based and sensing-based jamming behaviors. Despite being limited to electronic warfare scenarios, we hope that this work can pave the way for further research into antifragile communications.

show abstract

“…Additional literature on antijamming using a RL framework that was published after the material in this chapter includes [131][132][133][134].…”

Section: Related Workmentioning

confidence: 99%

Antifragile Communications

Lichtman

Vondal

Clancy

et al. 2018

IEEE Systems Journal

View full text Add to dashboard Cite

show abstract

“…Without loss of generality, the average energy of g(t) and modulated symbols E(|x m | 2 ) are normalized to unity. 1 …”

Section: System Modelmentioning

confidence: 99%

“…In order to prove that S E R i.e., p e is uniformly locally Lipschitz, we show that | p e ( j, SNR, JNR 1 …”

Section: Appendix a Proof Of Theoremmentioning

confidence: 99%

See 1 more Smart Citation

Jamming Bandits—A Novel Learning Method for Optimal Jamming

Amuru

Tekin

Schaar

et al. 2016

IEEE Trans. Wireless Commun.

Self Cite

View full text Add to dashboard Cite

Abstract-Can an intelligent jammer learn and adapt to unknown environments in an electronic warfare-type scenario? In this paper, we answer this question in the positive, by developing a cognitive jammer that adaptively and optimally disrupts the communication between a victim transmitter-receiver pair. We formalize the problem using a multiarmed bandit framework where the jammer can choose various physical layer parameters such as the signaling scheme, power level and the on-off/pulsing duration in an attempt to obtain power efficient jamming strategies. We first present online learning algorithms to maximize the jamming efficacy against static transmitter-receiver pairs and prove that these algorithms converge to the optimal (in terms of the error rate inflicted at the victim and the energy used) jamming strategy. Even more importantly, we prove that the rate of convergence to the optimal jamming strategy is sublinear, i.e., the learning is fast in comparison to existing reinforcement learning algorithms, which is particularly important in dynamically changing wireless environments. Also, we characterize the performance of the proposed bandit-based learning algorithm against multiple static and adaptive transmitter-receiver pairs.

show abstract

“…that is difficult to obtain in the actual environment. Other researchers solve the jamming problem with repeatedly interacting with the victim transmitter-receiver pair [23], combining optimization, game-theoretic theories and other theoretical tools. But these only take the situation that the user has a fixed strategy into consideration, or choose a strategy from a strategy set.…”

Section: Introductionmentioning

confidence: 99%

On the Performance of Deep Reinforcement Learning-Based Anti-Jamming Method Confronting Intelligent Jammer

Wang

Liu

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

With the development of access technologies and artificial intelligence, a deep reinforcement learning (DRL) algorithm is proposed into channel accessing and anti-jamming. Assuming the jamming modes are sweeping, comb, dynamic and statistic, the DRL-based method through training can almost perfectly avoid jamming signal and communicate successfully. Instead, in this paper, from the perspective of jammers, we investigate the performance of a DRL-based anti-jamming method. First of all, we design an intelligent jamming method based on reinforcement learning to combat the DRL-based user. Then, we theoretically analyze the condition when the DRL-based anti-jamming algorithm cannot converge, and provide the proof. Finally, in order to investigate the performance of DRL-based method, various scenarios where users with different communicating modes combat jammers with different jamming modes are compared. As the simulation results show, the theoretical analysis is verified, and the proposed RL-based jamming can effectively restrict the performance of DRL-based anti-jamming method.

show abstract

A systematic learning method for optimal jamming

Cited by 8 publications

References 19 publications

Antifragile Communications

Antifragile Communications

Jamming Bandits—A Novel Learning Method for Optimal Jamming

On the Performance of Deep Reinforcement Learning-Based Anti-Jamming Method Confronting Intelligent Jammer

Contact Info

Product

Resources

About