Wireless systems must be resilient to jamming attacks. Existing mitigation methods based on multi-antenna processing require knowledge of the jammer's transmit characteristics that may be difficult to acquire, especially for smart jammers that evade mitigation by transmitting only at specific instants. We propose a novel method to mitigate smart jamming attacks on the massive multi-user multiple-input multiple-output (MU-MIMO) uplink which does not require the jammer to be active at any specific instant. By formulating an optimization problem that unifies jammer estimation and mitigation, channel estimation, and data detection, we exploit that a jammer cannot change its subspace within a coherence interval. Theoretical results for our problem formulation show that its solution is guaranteed to recover the users' data symbols under certain conditions. We develop two efficient iterative algorithms for approximately solving the proposed problem formulation: MAED, a parameter-free algorithm which uses forward-backward splitting with a box symbol prior, and SO-MAED, which replaces the prior of MAED with soft-output symbol estimates that exploit the discrete transmit constellation and which uses deep unfolding to optimize algorithm parameters. We use simulations to demonstrate that the proposed algorithms effectively mitigate a wide range of smart jammers without a priori knowledge about the attack type.
more »
« less
Sensitivity of Dynamic Network Slicing to Deep Reinforcement Learning Based Jamming Attacks
In this paper, we consider multi-agent deep reinforcement learning (deep RL) based network slicing agents in a dynamic environment with multiple base stations and multiple users. We develop a deep RL based jammer with limited prior information and limited power budget. The goal of the jammer is to minimize the transmission rates achieved with network slicing and thus degrade the network slicing agents' performance. We design a jammer with both listening and jamming phases and address jamming location optimization as well as jamming channel optimization via deep RL. We evaluate the jammer at the optimized location, generating interference attacks in the optimized set of channels by switching between the jamming phase and listening phase. We show that the proposed jammer can significantly reduce the victims' performance without direct feedback or prior knowledge on the network slicing policies.
more »
« less
- Award ID(s):
- 2221875
- PAR ID:
- 10464791
- Date Published:
- Journal Name:
- 2023 IEEE 34th Annual Inter- national Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Low-resolution analog-to-digital converters (ADCs) simplify the design of millimeter-wave (mmWave) massive multi-user multiple-input multiple-output (MU-MIMO) basestations, but increase vulnerability to jamming attacks. As a remedy, we propose HERMIT (short for Hybrid jammER MITigation), a method that combines a hardware-friendly adaptive analog transform with a corresponding digital equalizer: The analog transform removes most of the jammer’s energy prior to data conversion; the digital equalizer suppresses jammer residues while detecting the legitimate transmit data. We provide theoretical results that establish the optimal analog transform as a function of the user equipments’ and the jammer’s channels. Using simulations with mmWave channel models, we demonstrate the superiority of HERMIT compared both to purely digital jammer mitigation as well as to a recent hybrid method that mitigates jammer interference with a nonadaptive analog transform.more » « less
-
ION ITM (Ed.)This paper describes the development, implementation, and testing of a GNSS jammer localizer using power measurement profiles collected during un-crewed aerial system (UAS) fly-bys. A linearized measurement equation based on the Friis power transmission formula is derived in which RF channel propagation parameters are grouped into a single parameter for estimation. Synchronized power and UAS position measurements are processed in a batch-type sequential non-linear least squares algorithm for simultaneous estimation of static jammer position and received power model parameters. We develop a low size, weight, power, and cost (SWAP-C) quad-rotor UAS test bed that can collect and time-stamp power measurements with UAS position. Since GNSS jamming is illegal, a LoRa 868 MHz transmitter is used as a surrogate GNSS jammer during field testing – providing Received Signal Strength Indicator (RSSI) measurements to the LoRa receiver onboard the UAS. Testing is conducted at the Virginia Tech Kentland Experimental Aerial Systems Lab, where emitter localization is evaluated for three different trajectories. Experimental performance analysis suggests that meter-level localization accuracy is achievable with prior knowledge on source location and by accounting for antenna gain pattern variations over time in the estimation process with a first order Gauss Markov Process.more » « less
-
Integrated sensing and communication (ISAC) systems traditionally presuppose that sensing and communication (S&C) channels remain approximately constant during their coherence time. However, a “DISCO” reconfigurable intelligent surface (DRIS), i.e., an illegitimate RIS with random, time-varying reflection properties that acts like a “disco ball,” introduces a paradigm shift that enables active channel aging more rapidly during the channel coherence time. In this letter, we investigate the impact of DISCO jamming attacks launched by a DRIS-based fully-passive jammer (FPJ) on an ISAC system. Specifically, an ISAC problem formulation and a corresponding waveform optimization are presented in which the ISAC waveform design considers the trade-off between the S&C performance and is formulated as a Pareto optimization problem. Moreover, a theoretical analysis is conducted to quantify the impact of DISCO jamming attacks. Numerical results are presented to evaluate the S&C performance under DISCO jamming attacks and to validate the derived theoretical analysis.more » « less
-
Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent’s inputs, which raises concerns about deploying such agents in the real world. To address this issue, we propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against lp-norm bounded adversarial attacks. Our framework is compatible with popular deep reinforcement learning algorithms and we demonstrate its performance with deep Q-learning, A3C and PPO. We experiment on three deep RL benchmarks (Atari, MuJoCo and ProcGen) to show the effectiveness of our robust training algorithm. Our RADIAL-RL agents consistently outperform prior methods when tested against attacks of varying strength and are more computationally efficient to train. In addition, we propose a new evaluation method called Greedy Worst-Case Reward (GWC) to measure attack agnostic robustness of deep RL agents. We show that GWC can be evaluated efficiently and is a good estimate of the reward under the worst possible sequence of adversarial attacks. All code used for our experiments is available at https://github.com/tuomaso/radial_rl_v2.more » « less