Aydin Sezgin

Aya Mostafa Ahmed, Udaya S. K. P. Miriya Thanthrige, Aydin Sezgin et al.

In this paper, we address the problem of direction of arrival (DOA) estimation for multiple targets in the presence of sensor failures in a sparse array. Generally, sparse arrays are known with very high-resolution capabilities, where N physical sensors can resolve up to $\mathcal{O}(N^2)$ uncorrelated sources. However, among the many configurations introduced in the literature, the arrays that provide the largest hole-free co-array are the most susceptible to sensor failures. We propose here two machine learning (ML) methods to mitigate the effect of sensor failures and maintain the DOA estimation performance and resolution. The first method enhances the conventional spatial smoothing using deep neural network (DNN), while the second one is an end-to-end data-driven method. Numerical results show that both approaches can significantly improve the performance of MRA with two failed sensors. The data-driven method can maintain the performance of the array with no failures at high signal-tonoise ratio (SNR). Moreover, both approaches can even perform better than the original array at low SNR thanks to the denoising effect of the proposed DNN

Kevin Weinberger, Robert-Jeron Reifert, Aydin Sezgin et al.

As 6G and beyond redefine connectivity, wireless networks become the foundation of critical operations, making resilience more essential than ever. With this shift, wireless systems cannot only take on vital services previously handled by wired infrastructures but also enable novel innovative applications that would not be possible with wired systems. As a result, there is a pressing demand for strategies that can adapt to dynamic channel conditions, interference, and unforeseen disruptions, ensuring seamless and reliable performance in an increasingly complex environment. Despite considerable research, existing resilience assessments lack comprehensive key performance indicators (KPIs), especially those quantifying its adaptability, which are vital for identifying a system's capacity to rapidly adapt and reallocate resources. In this work, we bridge this gap by proposing a novel framework that explicitly quantifies the adaption performance by augmenting the gradient of the system's rate function. To further enhance the network resilience, we integrate Reconfigurable Intelligent Surfaces (RISs) into our framework due to their capability to dynamically reshape the propagation environment while providing alternative channel paths. Numerical results show that gradient augmentation enhances resilience by improving adaptability under adverse conditions while proactively preparing for future disruptions.

Aymen Khaleel, Adam Umra, Aydin Sezgin

The reconfigurable intelligent surfaces detection and identification (RISs-ID) is a critical process that enables a base station (BS) to adaptively assign the appropriate RIS to a given user equipment (UE). This work proposes a novel modulation scheme to enhance the reliability of RIS-ID by reducing the miss detection and false-alarm probabilities. Specifically, we leverage the RIS's passive beamforming gain to enable over-the-air modulation of the RIS ID, combined with passive beam sweeping to extend detection coverage in angular space. The proposed modulation scheme is validated through computer simulations and prototype experiments, demonstrating its effectiveness in reducing miss-detection and false-alarm probabilities.

Adam Umra, Aya M. Ahmed, Aydin Sezgin

This paper proposes a reinforcement learning (RL)-aided cognitive framework for massive MIMO-based integrated sensing and communication (ISAC) systems employing a uniform planar array (UPA). The focus is on enhancing radar sensing performance in environments with unknown and dynamic disturbance characteristics. A Wald-type detector is employed for robust target detection under non-Gaussian clutter, while a SARSA-based RL algorithm enables adaptive estimation of target positions without prior environmental knowledge. Based on the RL-derived sensing information, a joint waveform optimization strategy is formulated to balance radar sensing accuracy and downlink communication throughput. The resulting design provides an adaptive trade-off between detection performance and achievable sum rate through an analytically derived closed-form solution. Monte Carlo simulations demonstrate that the proposed cognitive ISAC framework achieves significantly improved detection probability compared to orthogonal and non-learning adaptive baselines, while maintaining competitive communication performance. These results underline the potential of RL-assisted sensing for robust and spectrum-efficient ISAC in next-generation wireless networks.

Adam Umra, Aya Mostafa Ahmed, Aydin Sezgin

Motivated by the growing interest in integrated sensing and communication for 6th generation (6G) networks, this paper presents a cognitive Multiple-Input Multiple-Output (MIMO) radar system enhanced by reinforcement learning (RL) for robust multitarget detection in dynamic environments. The system employs a planar array configuration and adapts its transmitted waveforms and beamforming patterns to optimize detection performance in the presence of unknown two-dimensional (2D) disturbances. A robust Wald-type detector is integrated with a SARSA-based RL algorithm, enabling the radar to learn and adapt to complex clutter environments modeled by a 2D autoregressive process. Simulation results demonstrate significant improvements in detection probability compared to omnidirectional methods, particularly for low Signal-to-Noise Ratio (SNR) targets masked by clutter.

Robert-Jeron Reifert, Alaa Alameer Ahmad, Hayssam Dahrouj et al.

Future sixth-generation (6G) mobile networks are envisioned to be equipped with a diverse set of powerful, yet highly specialized, optimization experts. Such a promising vision is concurrently expected to give rise to the need for scalable mechanisms that can select, combine, and orchestrate such experts based on high-level intent and uncertainty descriptions. In this paper, we propose an agentic artificial intelligence (AI)-based network optimization framework that integrates mixture of experts (MoE) architectures with large language models (LLMs). Under the proposed framework, the employed LLM acts as a semantic gate to reason over operator objectives and dynamically compose suitable optimization agents. The proposed framework is formulated in a model-agnostic manner and bridges human-readable network intents with low-level resource allocation decisions, enabling flexible optimization across heterogeneous objectives and operating conditions. As a representative instantiation, we apply the framework to a joint communication and computing network and design a library of specialized optimization experts covering throughput, fairness, and delay-driven objectives under both regular and robust conditions. Numerical simulations demonstrate that the proposed agentic MoE framework consistently achieves near-optimal performance compared to exhaustive expert combinations while outperforming individual experts across diverse objectives, including delay minimization and throughput maximization.

Mariam Yahya, Aydin Sezgin, Setareh Maghsudi

As users in small cell networks increasingly rely on computation-intensive services, cloud-based access often results in high latency. Multi-access edge computing (MEC) mitigates this by bringing computational resources closer to end users, with small base stations (SBSs) serving as edge servers to enable low-latency service delivery. However, limited edge capacity makes it challenging to decide which services to deploy locally versus in the cloud, especially under unknown service demand and dynamic network conditions. To tackle this problem, we model service demand as a linear function of service attributes and formulate the service placement task as a linear bandit problem, where SBSs act as agents and services as arms. The goal is to identify the service that, when placed at the edge, offers the greatest reduction in total user delay compared to cloud deployment. We propose a distributed and adaptive multi-agent best-arm identification (BAI) algorithm under a fixed-confidence setting, where SBSs collaborate to accelerate learning. Simulations show that our algorithm identifies the optimal service with the desired confidence and achieves near-optimal speedup, as the number of learning rounds decreases proportionally with the number of SBSs. We also provide theoretical analysis of the algorithm's sample complexity and communication overhead.

Robert-Jeron Reifert, Hayssam Dahrouj, Alaa Alameer Ahmad et al.

The convergence of communication and computation, along with the integration of machine learning and artificial intelligence, stand as key empowering pillars for the sixth-generation of communication systems (6G). This paper considers a network of one base station serving a number of devices simultaneously using spatial multiplexing. The paper then presents an innovative deep learning-based approach to simultaneously manage the transmit and computing powers, alongside computation allocation, amidst uncertainties in both channel and computing states information. More specifically, the paper aims at proposing a robust solution that minimizes the worst-case delay across the served devices subject to computation and power constraints. The paper uses a deep neural network (DNN)-based solution that maps estimated channels and computation requirements to optimized resource allocations. During training, uncertainty samples are injected after the DNN output to jointly account for both communication and computation estimation errors. The DNN is then trained via backpropagation using the robust utility, thus implicitly learning the uncertainty distributions. Our results validate the enhanced robust delay performance of the joint uncertainty injection versus the classical DNN approach, especially in high channel and computational uncertainty regimes.

Paul Staat, Simon Mulzer, Stefan Roth et al.

Wireless radio channels are known to contain information about the surrounding propagation environment, which can be extracted using established wireless sensing methods. Thus, today's ubiquitous wireless devices are attractive targets for passive eavesdroppers to launch reconnaissance attacks. In particular, by overhearing standard communication signals, eavesdroppers obtain estimations of wireless channels which can give away sensitive information about indoor environments. For instance, by applying simple statistical methods, adversaries can infer human motion from wireless channel observations, allowing to remotely monitor premises of victims. In this work, building on the advent of intelligent reflecting surfaces (IRSs), we propose IRShield as a novel countermeasure against adversarial wireless sensing. IRShield is designed as a plug-and-play privacy-preserving extension to existing wireless networks. At the core of IRShield, we design an IRS configuration algorithm to obfuscate wireless channels. We validate the effectiveness with extensive experimental evaluations. In a state-of-the-art human motion detection attack using off-the-shelf Wi-Fi devices, IRShield lowered detection rates to 5% or less.

Udaya S. K. P. Miriya Thanthrige, Peter Jung, Aydin Sezgin

We address the detection of material defects, which are inside a layered material structure using compressive sensing based multiple-input and multiple-output (MIMO) wireless radar. Here, the strong clutter due to the reflection of the layered structure's surface often makes the detection of the defects challenging. Thus, sophisticated signal separation methods are required for improved defect detection. In many scenarios, the number of defects that we are interested in is limited and the signaling response of the layered structure can be modeled as a low-rank structure. Therefore, we propose joint rank and sparsity minimization for defect detection. In particular, we propose a non-convex approach based on the iteratively reweighted nuclear and $\ell_1-$norm (a double-reweighted approach) to obtain a higher accuracy compared to the conventional nuclear norm and $\ell_1-$norm minimization. To this end, an iterative algorithm is designed to estimate the low-rank and sparse contributions. Further, we propose deep learning to learn the parameters of the algorithm (i.e., algorithm unfolding) to improve the accuracy and the speed of convergence of the algorithm. Our numerical results show that the proposed approach outperforms the conventional approaches in terms of mean square errors of the recovered low-rank and sparse components and the speed of convergence.

Stefan Roth, Stefano Tomasin, Marco Maso et al.

In fifth-generation (5G) cellular networks, users feed back to the base station the index of the precoder (from a codebook) to be used for downlink transmission. The precoder is strongly related to the user channel and in turn to the user position within the cell. We propose a method by which an external attacker determines the user position by passively overhearing this unencrypted layer-2 feedback signal. The attacker first builds a map of fed back precoder indices in the cell. Then, by overhearing the precoder index fed back by the victim user, the attacker finds its position on the map. We focus on the type-I single-panel codebook, which today is the only mandatory solution in the 3GPP standard. We analyze the attack and assess the obtained localization accuracy against various parameters. We analyze the localization error of a simplified precoder feedback model and describe its asymptotic localization precision. We also propose a mitigation against our attack, wherein the user randomly selects the precoder among those providing the highest rate. Simulations confirm that the attack can achieve a high localization accuracy, which is significantly reduced when the mitigation solution is adopted, at the cost of a negligible rate degradation.

Pascal Zimmer, Roland Weinreich, Christian T. Zenger et al.

In this paper, we investigate physical-layer security (PLS) methods for proximity-based group-key establishment and proof of location. Fields of application include secure car-to-car communication, privacy-preserving and secure distance evidence for healthcare or location-based feature activation. Existing technologies do not solve the problem satisfactorily, due to communication restrictions, e.g., ultra-wide band (UWB) based time of flight measurements, or trusted hardware, e.g., using global navigation satellite system (GNSS) positioning data. We introduce PLS as a solution candidate. It is information theoretically secure, which also means post-quantum resistant, and has the potential to run on resource constrained devices with low latency. Furthermore, we use wireless channel properties of satellite-to-Earth links, demonstrate the first feasibility study using off-the-shelf hardware testbeds and present first evaluation results and future directions for research.

Aya Mostafa Ahmed, Udaya Sampath K. P. Miriya Thanthrige, Aly El Gamal et al.

We present a MUSIC-based Direction of Arrival (DOA) estimation strategy using small antenna arrays, via employing deep learning for reconstructing the signals of a virtual large antenna array. Not only does the proposed strategy deliver significantly better performance than simply plugging the incoming signals into MUSIC, but surprisingly, the performance is also better than directly using an actual large antenna array with MUSIC for high angle ranges and low test SNR values. We further analyze the best choice for the training SNR as a function of the test SNR, and observe dramatic changes in the behavior of this function for different angle ranges.

Kashmira Shinde, Jongseok Lee, Matthias Humt et al.

This paper presents an end-to-end multi-modal learning approach for monocular Visual-Inertial Odometry (VIO), which is specifically designed to exploit sensor complementarity in the light of sensor degradation scenarios. The proposed network makes use of a multi-head self-attention mechanism that learns multiplicative interactions between multiple streams of information. Another design feature of our approach is the incorporation of the model uncertainty using scalable Laplace Approximation. We evaluate the performance of the proposed approach by comparing it against the end-to-end state-of-the-art methods on the KITTI dataset and show that it achieves superior performance. Importantly, our work thereby provides an empirical evidence that learning multiplicative interactions can result in a powerful inductive bias for increased robustness to sensor failures.

Aya Mostafa Ahmed, Alaa Alameer Ahmad, Stefano Fortunati et al.

This paper considers the problem of multi-target detection for massive multiple input multiple output (MMIMO) cognitive radar (CR). The concept of CR is based on the perception-action cycle that senses and intelligently adapts to the dynamic environment in order to optimally satisfy a specific mission. However, this usually requires a priori knowledge of the environmental model, which is not available in most cases. We propose a reinforcement learning (RL) based algorithm for cognitive multi-target detection in the presence of unknown disturbance statistics. The radar acts as an agent that continuously senses the unknown environment (i.e., targets and disturbance) and consequently optimizes transmitted waveforms in order to maximize the probability of detection ($P_\mathsf{D}$) by focusing the energy in specific range-angle cells (i.e., beamforming). Furthermore, we propose a solution to the beamforming optimization problem with less complexity than the existing methods. Numerical simulations are performed to assess the performance of the proposed RL-based algorithm in both stationary and dynamic environments. The RL based beamforming is compared to the conventional omnidirectional approach with equal power allocation and to adaptive beamforming with no RL. As highlighted by the proposed numerical results, our RL-based beamformer outperforms both approaches in terms of target detection performance. The performance improvement is even particularly remarkable under environmentally harsh conditions such as low SNR, heavy-tailed disturbance and rapidly changing scenarios.

Jaber Kakar, Aydin Sezgin

In this paper, we consider the over-the-air computation of sums. Specifically, we wish to compute $M\geq 2$ sums $s_m=\sum_{k\in\mathcal{D}m}x_k$ over a shared complex-valued MAC at once with minimal mean-squared error ($\mathsf{MSE}$). Finding appropriate Tx-Rx scaling factors balance between a low error in the computation of $s_n$ and the interference induced by it in the computation of other sums $s_m$, $m\neq n$. In this paper, we are interested in designing an optimal Tx-Rx scaling policy that minimizes the mean-squared error $\max_{m\in[1:M]}\mathsf{MSE}_m$ subject to a Tx power constraint with maximum power $P$. We show that an optimal design of the Tx-Rx scaling policy $\left(\bar{\mathbf{a}},\bar{\mathbf{b}}\right)$ involves optimizing (a) their phases and (b) their absolute values in order to (i) decompose the computation of $M$ sums into, respectively, $M_R$ and $M_I$ ($M=M_R+M_I$) calculations over real and imaginary part of the Rx signal and (ii) to minimize the computation over each part -- real and imaginary -- individually. The primary focus of this paper is on (b). We derive conditions (i) on the feasibility of the optimization problem and (ii) on the Tx-Rx scaling policy of a local minimum for $M_w=2$ computations over the real ($w=R$) or the imaginary ($w=I$) part. Extensive simulations over a single Rx chain for $M_w=2$ show that the level of interference in terms of $ΔD=|\mathcal{D}_2|-|\mathcal{D}_1|$ plays an important role on the ergodic worst-case $\mathsf{MSE}$. At very high $\mathsf{SNR}$, typically only the sensor with the weakest channel transmits with full power while all remaining sensors transmit with less to limit the interference. Interestingly, we observe that due to residual interference, the ergodic worst-case $\mathsf{MSE}$ is not vanishing; rather, it converges to $\frac{|\mathcal{D}_1||\mathcal{D}_2|}{K}$ as $\mathsf{SNR}\rightarrow\infty$.

Jaber Kakar, Anton Khristoforov, Seyedhamed Ebadifar et al.

In secure distributed matrix multiplication (SDMM) the multiplication $\mathbf{A}\mathbf{B}$ from two private matrices $\mathbf{A}$ and $\mathbf{B}$ is outsourced by a user to $N$ distributed servers. In $\ell$-SDMM, the goal is to a design a joint communication-computation procedure that optimally balances conflicting communication and computation metrics without leaking any information on both $\mathbf{A}$ and $\mathbf{B}$ to any set of $\ell\leq N$ servers. To this end, the user applies coding with $\tilde{\mathbf{A}}_i$ and $\tilde{\mathbf{B}}_i$ representing encoded versions of $\mathbf{A}$ and $\mathbf{B}$ destined to the $i$-th server. Now, SDMM involves multiple tradeoffs. One such tradeoff is the tradeoff between uplink (UL) and downlink (DL) costs. To find a good balance between these two metrics, we propose two schemes which we term USCSA and GSCSA that are based on secure cross subspace alignment (SCSA). We show that there are various scenarios where they outperform existing SDMM schemes from the literature with respect to the UL-DL efficiency. Next, we implement schemes from the literature, including USCSA and GSCSA, and test their performance on Amazon EC2. Our numerical results show that USCSA and GSCSA establish a good balance between the time spend on the communication and computation in SDMMs. This is because they combine advantages of polynomial codes, namely low time for the upload of $\left(\tilde{\mathbf{A}}_i,\tilde{\mathbf{B}}_i\right)_{i=1}^{N}$ and the computation of $\mathbf{O}_i=\tilde{\mathbf{A}}_i\tilde{\mathbf{B}}_i$, with those of SCSA, being a low timing overhead for the download of $\left(\mathbf{O}_i\right)_{i=1}^{N}$ and the decoding of $\mathbf{A}\mathbf{B}$.

Christan Zenger, Hendrik Vogt, Jan Zimmer et al.

Channel-reciprocity based key generation (CRKG) has gained significant importance as it has recently been proposed as a potential lightweight security solution for IoT devices. However, the impact of the attacker's position in close range has only rarely been evaluated in practice, posing an open research problem about the security of real-world realizations. Furthermore, this would further bridge the gap between theoretical channel models and their practice-oriented realizations. For security metrics, we utilize cross-correlation, mutual information, and a lower bound on secret-key capacity. We design a practical setup of three parties such that the channel statistics, although based on joint randomness, are always reproducible. We run experiments to obtain channel states and evaluate the aforementioned metrics for the impact of an attacker depending on his position. It turns out the attacker himself affects the outcome, which has not been adequately regarded yet in standard channel models.

Hendrik Vogt, Zohaib Hassan Awan, Aydin Sezgin

Full-duplex (FD) communication is regarded as a key technology in future 5G and Internet of Things (IoT) systems. In addition to high data rate constraints, the success of these systems depends on the ability to allow for confidentiality and security. Secret-key agreement from reciprocal wireless channels can be regarded as a valuable supplement for security at the physical layer. In this work, we study the role of FD communication in conjunction with secret-key agreement. We first introduce two complementary key generation models for FD and half-duplex (HD) settings and compare the performance by introducing the key-reconciliation function. Furthermore, we study the impact of the so called probing-reconciliation trade-off, the role of a strong eavesdropper and analyze the system in the high SNR regime. We show that under certain conditions, the FD mode enforces a deteriorating impact on the capabilities of the eavesdropper and offers several advantages in terms of secret-key rate over the conventional HD setups. Our analysis reveals as an interesting insight that perfect self-interference cancellation is not necessary in order to obtain performance gains over the HD mode.

Hendrik Vogt, Aydin Sezgin

Secret-key generation in a wireless environment exploiting the randomness and reciprocity of the channel gains is considered. A new channel model is proposed which takes into account the effect of reflections (or re-radiations) from receive antenna elements, thus capturing an physical property of practical antennas. It turns out that the reflections have a deteriorating effect on the achievable secret-key rate between the legitimate nodes at high signal-to-noise-power-ratio (SNR). The insights provide guidelines in the design and operation of communication systems using the properties of the wireless channel to prevent eavesdropping.