arXiv subjects

Narayan B. Mandayam

Publications and source records attributed to Narayan B. Mandayam.

At least 19 recordsLinked to original sources

arXiv2026

Modeling and Mitigation of 7.125-7.40 GHz Terrestrial Network RFI on the Passive Earth Exploration Satellite Service in 6.725-7.125 GHz Band

The 7.125-7.4 GHz band is attractive for next generation Terrestrial Network (TN) deployments owing to the large bandwidths available and favorable propagation characteristics. Furthermore, recent U.S. Presidential actions have cleared the usage of this band for 6G by stipulating relocation of federal incumbents that share this band. However, this deployment can only be successful if we can also guarantee coexistence of these networks with existing incumbents operating in adjacent bands. This paper presents a comprehensive analysis of the Radio Frequency Interference (RFI) caused by the proposed TNs in the 7.125-7.4 GHz band at passive Earth Exploration Satellite Service (EESS) sensors that operate in the adjacent 6.725-7.125 GHz band. Using TN base stations (BSs) equipped with filtennas (filtering antennas) as well as transmit precoders for RFI mitigation, we carry out an RFI analysis that accounts for increasing BS deployments in the contiguous U.S. over a 10 year period from 2030 to 2040. We also characterize the size of the guard bands needed to protect the EESS sensors for different BS deployment densities. With appropriate filtenna and precoder design, our results reveal that a 100 Mbps increase in the rate requirements of the TN users results in an RFI increase of roughly 2.45 dB at the EESS sensors. For a 25 MHz Guard Band, simulations show that in 2030, there is no significant RFI for user rates upto 500 Mbps. However, the same systems in 2040 would cause RFI that is around 4 dB above the ITU mandated threshold for passive EESS sensors. This would need to be countered by (a) increasing Guard Band width to 35 MHz, or (b) by reducing the user data rate requirements to 300 Mbps.

eess.SP↗

arXiv2025

Balancing Timeliness and Privacy in Discrete-Time Updating Systems

We study the trade-off between Age of Information (AoI) and maximal leakage (MaxL) in discrete-time status updating systems. A source generates time-stamped update packets that are processed by a server that delivers them to a monitor. An adversary, who eavesdrops on the server-monitor link, wishes to infer the timing of the underlying source update sequence. The server must balance the timeliness of the status information at the monitor against the timing information leaked to the adversary. We consider a model with Bernoulli source updates under two classes of Last-Come-First-Served (LCFS) service policies: (1) Coupled policies that tie the server's deliveries to the update arrival process in a preemptive queue; (2) Decoupled (dumping) policies in which the server transmits its freshest update according to a schedule that is independent of the update arrivals. For each class, we characterize the structure of the optimal policy that minimizes AoI for a given MaxL rate. Our analysis reveals that decoupled dumping policies offer a superior age-leakage trade-off to coupled policies. When subject to a MaxL constraint, we prove that the optimal dumping strategy is achieved by dithering between two adjacent deterministic dump periods.

eess.SY↗

arXiv2025

Mental Accounts for Actions: EWA-Inspired Attention in Decision Transformers

Transformers have emerged as a compelling architecture for sequential decision-making by modeling trajectories via self-attention. In reinforcement learning (RL), they enable return-conditioned control without relying on value function approximation. Decision Transformers (DTs) exploit this by casting RL as supervised sequence modeling, but they are restricted to offline data and lack exploration. Online Decision Transformers (ODTs) address this limitation through entropy-regularized training on on-policy rollouts, offering a stable alternative to traditional RL methods like Soft Actor-Critic, which depend on bootstrapped targets and reward shaping. Despite these advantages, ODTs use standard attention, which lacks explicit memory of action-specific outcomes. This leads to inefficiencies in learning long-term action effectiveness. Inspired by cognitive models such as Experience-Weighted Attraction (EWA), we propose Experience-Weighted Attraction with Vector Quantization for Online Decision Transformers (EWA-VQ-ODT), a lightweight module that maintains per-action mental accounts summarizing recent successes and failures. Continuous actions are routed via direct grid lookup to a compact vector-quantized codebook, where each code stores a scalar attraction updated online through decay and reward-based reinforcement. These attractions modulate attention by biasing the columns associated with action tokens, requiring no change to the backbone or training objective. On standard continuous-control benchmarks, EWA-VQ-ODT improves sample efficiency and average return over ODT, particularly in early training. The module is computationally efficient, interpretable via per-code traces, and supported by theoretical guarantees that bound the attraction dynamics and its impact on attention drift.

cs.LG↗

arXiv2025

Human-AI Collaboration in Cloud Security: Cognitive Hierarchy-Driven Deep Reinforcement Learning

Given the complexity of multi-tenant cloud environments and the growing need for real-time threat mitigation, Security Operations Centers (SOCs) must adopt AI-driven adaptive defense mechanisms to counter Advanced Persistent Threats (APTs). However, SOC analysts face challenges in handling adaptive adversarial tactics, requiring intelligent decision-support frameworks. We propose a Cognitive Hierarchy Theory-driven Deep Q-Network (CHT-DQN) framework that models interactive decision-making between SOC analysts and AI-driven APT bots. The SOC analyst (defender) operates at cognitive level-1, anticipating attacker strategies, while the APT bot (attacker) follows a level-0 policy. By incorporating CHT into DQN, our framework enhances adaptive SOC defense using Attack Graph (AG)-based reinforcement learning. Simulation experiments across varying AG complexities show that CHT-DQN consistently achieves higher data protection and lower action discrepancies compared to standard DQN. A theoretical lower bound further confirms its superiority as AG complexity increases. A human-in-the-loop (HITL) evaluation on Amazon Mechanical Turk (MTurk) reveals that SOC analysts using CHT-DQN-derived transition probabilities align more closely with adaptive attackers, leading to better defense outcomes. Moreover, human behavior aligns with Prospect Theory (PT) and Cumulative Prospect Theory (CPT): participants are less likely to reselect failed actions and more likely to persist with successful ones. This asymmetry reflects amplified loss sensitivity and biased probability weighting -- underestimating gains after failure and overestimating continued success. Our findings highlight the potential of integrating cognitive models into deep reinforcement learning to improve real-time SOC decision-making for cloud security.

cs.CR↗

arXiv2023

Programming Wireless Security through Learning-Aided Spatiotemporal Digital Coding Metamaterial Antenna

The advancement of future large-scale wireless networks necessitates the development of cost-effective and scalable security solutions. Conventional cryptographic methods, due to their computational and key management complexity, are unable to fulfill the low-latency and scalability requirements of these networks. Physical layer (PHY) security has been put forth as a cost-effective alternative to cryptographic mechanisms that can circumvent the need for explicit key exchange between communication devices, owing to the fact that PHY security relies on the physics of the signal transmission for providing security. In this work, a space-time-modulated digitally-coded metamaterial (MTM) leaky wave antenna (LWA) is proposed that can enable PHY security by achieving the functionalities of directional modulation (DM) using a machine learning-aided branch and bound (B&B) optimized coding sequence. From the theoretical perspective, it is first shown that the proposed space-time MTM antenna architecture can achieve DM through both the spatial and spectral manipulation of the orthogonal frequency division multiplexing (OFDM) signal received by a user equipment. Simulation results are then provided as proof-of-principle, demonstrating the applicability of our approach for achieving DM in various communication settings. To further validate our simulation results, a prototype of the proposed architecture controlled by a field-programmable gate array (FPGA) is realized, which achieves DM via an optimized coding sequence carried out by the learning-aided branch-and-bound algorithm corresponding to the states of the MTM LWA's unit cells. Experimental results confirm the theory behind the space-time-modulated MTM LWA in achieving DM, which is observed via both the spectral harmonic patterns and bit error rate (BER) measurements.

eess.SP↗

arXiv2022

Watch from sky: machine-learning-based multi-UAV network for predictive police surveillance

This paper presents the watch-from-sky framework, where multiple unmanned aerial vehicles (UAVs) play four roles, i.e., sensing, data forwarding, computing, and patrolling, for predictive police surveillance. Our framework is promising for crime deterrence because UAVs are useful for collecting and distributing data and have high mobility. Our framework relies on machine learning (ML) technology for controlling and dispatching UAVs and predicting crimes. This paper compares the conceptual model of our framework against the literature. It also reports a simulation of UAV dispatching using reinforcement learning and distributed ML inference over a lossy UAV network.

cs.LG↗

arXiv2021

A hybrid model-based and learning-based approach for classification using limited number of training samples

The fundamental task of classification given a limited number of training data samples is considered for physical systems with known parametric statistical models. The standalone learning-based and statistical model-based classifiers face major challenges towards the fulfillment of the classification task using a small training set. Specifically, classifiers that solely rely on the physics-based statistical models usually suffer from their inability to properly tune the underlying unobservable parameters, which leads to a mismatched representation of the system's behaviors. Learning-based classifiers, on the other hand, typically rely on a large number of training data from the underlying physical process, which might not be feasible in most practical scenarios. In this paper, a hybrid classification method -- termed HyPhyLearn -- is proposed that exploits both the physics-based statistical models and the learning-based classifiers. The proposed solution is based on the conjecture that HyPhyLearn would alleviate the challenges associated with the individual approaches of learning-based and statistical model-based classifiers by fusing their respective strengths. The proposed hybrid approach first estimates the unobservable model parameters using the available (suboptimal) statistical estimation procedures, and subsequently use the physics-based statistical models to generate synthetic data. Then, the training data samples are incorporated with the synthetic data in a learning-based classifier that is based on domain-adversarial training of neural networks. Specifically, in order to address the mismatch problem, the classifier learns a mapping from the training data and the synthetic data to a common feature space. Simultaneously, the classifier is trained to find discriminative features within this space in order to fulfill the classification task.

cs.LG↗

arXiv2021

Network Traffic Shaping for Enhancing Privacy in IoT Systems

Motivated by privacy issues caused by inference attacks on user activities in the packet sizes and timing information of Internet of Things (IoT) network traffic, we establish a rigorous event-level differential privacy (DP) model on infinite packet streams. We propose a memoryless traffic shaping mechanism satisfying a first-come-first-served queuing discipline that outputs traffic dependent on the input using a DP mechanism. We show that in special cases the proposed mechanism recovers existing shapers which standardize the output independently from the input. To find the optimal shapers for given levels of privacy and transmission efficiency, we formulate the constrained problem of minimizing the expected delay per packet and propose using the expected queue size across time as a proxy. We further show that the constrained minimization is a convex program. We demonstrate the effect of shapers on both synthetic data and packet traces from actual IoT devices. The experimental results reveal inherent privacy-overhead tradeoffs: more shaping overhead provides better privacy protection. Under the same privacy level, there naturally exists a tradeoff between dummy traffic and delay. When dealing with heavier or less bursty input traffic, all shapers become more overhead-efficient. We also show that increased traffic from a larger number of IoT devices makes guaranteeing event-level privacy easier. The DP shaper offers tunable privacy that is invariant with the change in the input traffic distribution and has an advantage in handling burstiness over traffic-independent shapers. This approach well accommodates heterogeneous network conditions and enables users to adapt to their privacy/overhead demands.

eess.SP↗

arXiv2021

A Game-Theoretic Analysis of Competitive Editing in Wikipedia: Contributors' Effort to Influence Articles and the Community's Attempt to Ensure Neutrality

Peer production, such as the collaborative authoring of Wikipedia articles, involves both cooperation and competition between contributors, and we focus on the latter. As individuals, contributors compete to align Wikipedia articles with their personal perspectives. As a community, they work collectively to ensure a neutral point of view (NPOV). We study the interplay between individuals' competition and the community's endeavor to ensure neutrality. We develop a two-level game-theoretic model, modeling the interactions of ownership-motivated individuals and neutrality-seeking communal mechanisms as a Stackelberg game. We present our model's predictions regarding the relation between contributors' effort (i.e. typical size of edit) and benefits (i.e. the portion of the article they eventually ``own''). We validate the model's prediction through an empirical analysis, by studying the interactions of 219,811 distinct contributors that co-produced 864 Wikipedia articles over a decade. The analysis and empirical results suggest that contributors who make large edits (``creators'') eventually lose the article's ownership to those who refine the articles and typically make smaller edits (``curators''). Whereas neutrality-seeking mechanisms are essential for ensuring that ownership is not concentrated within a small number of contributors, our findings suggest that the burden of excessive governance may deter contributors from participating.

cs.GT↗

arXiv2021

Prosumer Behavior: Decision Making with Bounded Horizon

Most studies of prosumer decision making in the smart grid have focused on single, temporally discrete decisions within the framework of expected utility theory (EUT) and behavioral theories such as prospect theory. In this work, we study prosumer decision making in a more natural, ongoing market situation in which a prosumer has to decide every day whether to sell any surplus energy units generated by the solar panels on her roof or hold (store) the energy units in anticipation of a future sale at a better price. Within this context, we propose a new behavioral model that extends EUT to take into account the notion of a bounded temporal horizon over which various decision parameters are considered. Specifically, we introduce the notion of a bounded time window (the number of upcoming days over which a prosumer evaluates the probability that each possible price will be the highest) that prosumers implicitly impose on their decision making in arriving at hold or sell decisions. The new behavioral model assumes that humans make decisions that will affect their lives within a bounded time window regardless of how far into the future their units may be sold. Modeling the utility of the prosumer using parameters such as the offered price on a day, the number of energy units the prosumer has available for sale on a day, and the probabilities of the forecast prices, we fit both traditional EUT and the proposed behavioral model with bounded time windows to data collected from 57 homeowners over 68 days in a simulated energy market. Each prosumer generated surplus units of solar power and had the opportunity to sell those units to the local utility at the price set that day by the utility or hold the units for sale in the future. For most participants, a bounded horizon in the range of 4-5 days provided a much better fit to their responses than was found for the traditional (unbounded) EUT model

eess.SY↗

arXiv2020

Estimation of Individual Device Contributions for Incentivizing Federated Learning

Federated learning (FL) is an emerging technique used to train a machine-learning model collaboratively using the data and computation resource of the mobile devices without exposing privacy-sensitive user data. Appropriate incentive mechanisms that motivate the data and mobile-device owner to participate in FL is key to building a sustainable platform for FL. However, it is difficult to evaluate the contribution level of the devices/owners to determine appropriate rewards without large computation and communication overhead. This paper proposes a computation-and communication-efficient method of estimating a participating device's contribution level. The proposed method enables such estimation during a single FL training process, there by reducing the need for traffic and computation overhead. The performance evaluations using the MNIST dataset show that the proposed method estimates individual participants' contributions accurately with 46-49% less computation overhead and no communication overhead than a naive estimation method.

cs.LG↗

arXiv2020

Learning-Aided Physical Layer Attacks Against Multicarrier Communications in IoT

Internet-of-Things (IoT) devices that are limited in power and processing are susceptible to physical layer (PHY) spoofing (signal exploitation) attacks owing to their inability to implement a full-blown protocol stack for security. The overwhelming adoption of multicarrier techniques such as orthogonal frequency division multiplexing (OFDM) for the PHY layer makes IoT devices further vulnerable to PHY spoofing attacks. These attacks which aim at injecting bogus/spurious data into the receiver, involve inferring transmission parameters and finding PHY characteristics of the transmitted signals so as to spoof the received signal. Non-contiguous (NC) OFDM systems have been argued to have low probability of exploitation (LPE) characteristics against classic attacks based on cyclostationary analysis, and the corresponding PHY has been deemed to be secure. However, with the advent of machine learning (ML) algorithms, adversaries can devise data-driven attacks to compromise such systems. It is in this vein that PHY spoofing performance of adversaries equipped with supervised and unsupervised ML tools are investigated in this paper. The supervised ML approach is based on deep neural networks (DNN) while the unsupervised one employs variational autoencoders (VAEs). In particular, VAEs are shown to be capable of learning representations from NC-OFDM signals related to their PHY characteristics such as frequency pattern and modulation scheme, which are useful for PHY spoofing. In addition, a new metric based on the disentanglement principle is proposed to measure the quality of such learned representations. Simulation results demonstrate that the performance of the spoofing adversaries highly depends on the subcarriers' allocation patterns. Particularly, it is shown that utilizing a random subcarrier occupancy pattern secures NC-OFDM systems against ML-based attacks.

cs.LG↗

arXiv2019

Colonel Blotto Game for Secure State Estimation in Interdependent Critical Infrastructure

Securing the physical components of a city's interdependent critical infrastructure (ICI) such as power, natural gas, and water systems is a challenging task due to their interdependence and a large number of involved sensors. In this paper, using a novel integrated state-space model that captures the interdependence, a two-stage cyber attack on an ICI is studied in which the attacker first compromises the ICI's sensors by decoding their messages, and, subsequently, it alters the compromised sensors' data to cause state estimation errors. To thwart such attacks, the administrator of each critical infrastructure (CI) must assign protection levels to the sensors based on their importance in the state estimation process. To capture the interdependence between the attacker and the ICI administrator's actions and analyze their interactions, a Colonel Blotto game framework is proposed. The mixed-strategy Nash equilibrium of this game is derived analytically. At this equilibrium, it is shown that the administrator can strategically randomize between the protection levels of the sensors to deceive the attacker. Simulation results coupled with theoretical analysis show that, using the proposed game, the administrator can reduce the state estimation error by at least $ 50\% $ compared to a non-strategic approach that assigns protection levels proportional to sensor values.

eess.SY↗

arXiv2019

Learning-based Resource Optimization in Ultra Reliable Low Latency HetNets

In this paper, the problems of user offloading and resource optimization are jointly addressed to support ultra-reliable and low latency communications (URLLC) in HetNets. In particular, a multi-tier network with a single macro base station (MBS) and multiple overlaid small cell base stations (SBSs) is considered that includes users with different latency and reliability constraints. Modeling the latency and reliability constraints of users with probabilistic guarantees, the joint problem of user offloading and resource allocation (JUR) in a URLLC setting is formulated as an optimization problem to minimize the cost of serving users for the MBS. In the considered scheme, SBSs bid to serve URLLC users under their coverage at a given price, and the MBS decides whether to serve each user locally or to offload it to one of the overlaid SBSs. Since the JUR optimization is NP-hard, we propose a low complexity learning-based heuristic method (LHM) which includes a support vector machine-based user association model and a convex resource optimization (CRO) algorithm. To further reduce the delay, we propose an alternating direction method of multipliers (ADMM)-based solution to the CRO problem. Simulation results show that using LHM, the MBS significantly decreases the spectrum access delay for users (by $\sim$ 93\%) as compared to JUR, while also reducing its bandwidth and power costs in serving users (by $\sim$ 33\%) as compared to directly serving users without offloading.

cs.NI↗

arXiv2018

Cyber-Physical Security and Safety of Autonomous Connected Vehicles: Optimal Control Meets Multi-Armed Bandit Learning

Autonomous connected vehicles (ACVs) rely on intra-vehicle sensors such as camera and radar as well as inter-vehicle communication to operate effectively. This reliance on cyber components exposes ACVs to cyber and physical attacks in which an adversary can manipulate sensor readings and physically take control of an ACV. In this paper, a comprehensive framework is proposed to thwart cyber and physical attacks on ACV networks. First, an optimal safe controller for ACVs is derived to maximize the street traffic flow while minimizing the risk of accidents by optimizing ACV speed and inter-ACV spacing. It is proven that the proposed controller is robust to physical attacks which aim at making ACV systems instable. To improve the cyber-physical security of ACV systems, next, data injection attack (DIA) detection approaches are proposed to address cyber attacks on sensors and their physical impact on the ACV system. To comprehensively design the DIA detection approaches, ACV sensors are characterized in two subsets based on the availability of a-priori information about their data. For sensors having a prior information, a DIA detection approach is proposed and an optimal threshold level is derived for the difference between the actual and estimated values of sensors data which enables ACV to stay robust against cyber attacks. For sensors having no prior information, a novel multi-armed bandit (MAB) algorithm is proposed to enable ACV to securely control its motion. Simulation results show that the proposed optimal safe controller outperforms current state of the art controllers by maximizing the robustness of ACVs to physical attacks. The results also show that the proposed DIA detection approaches, compared to Kalman filtering, can improve the security of ACV sensors against cyber attacks and ultimately improve the physical robustness of an ACV system.

eess.SY↗

arXiv2018

Joint User Association and Resource Allocation Optimization for Ultra Reliable Low Latency HetNets

Ensuring ultra-reliable and low latency communications (URLLC) is necessary for enabling delay critical applications in 5G HetNets. We propose a joint user to BS association and resource optimization method that is attractive for URLLC in HetNets with Cellular Base Stations (CBSs) and Small Cell Base Stations (SBSs), while also reducing energy and bandwidth consumption. In our scheme, CBSs share portions of the available spectrum with SBSs, and they in exchange, provide data service to the users in their coverage area. We first show that the CBSs optimal resource allocation (ORA) problem is NP-hard and computationally intractable for large number of users. Then, to reduce its time complexity, we propose a relaxed heuristic method (RHM) which breaks down the original ORA problem into a heuristic user association (HUA) algorithm and a convex resource allocation (CRA) optimization problem. Simulation results show that the proposed heuristic method decreases the time complexity of finding the optimal solution for CBS's significantly, thereby benefiting URLLC. It also helps the CBSs to save energy by offloading users to SBSs. In our simulations, the spectrum access delay for cellular users is reduced by 93\% and the energy consumption is reduced by 33\%, while maintaining the full service rate.

cs.NI↗

arXiv2018

Impact of End-User Behavior on User/Network Association in HetNets

We study the impact of end-user behavior on user/network association in a HetNet with multiple service providers (SPs). Specifically, we consider the uncertainty in the service guarantees offered by SPs in a HetNet, and use Prospect Theory (PT) to model end-user decision making. We formulate user association with SPs as a multiple leader Stackelberg game where each SP offers a data rate to each user with a certain service guarantee and at a certain price, while the user chooses the best offer among multiple such bids. Using the specific example of a HetNet with one cellular base station and one WiFi access point, we show that when the end users underestimate the advertised service guarantees, then some of the Nash Equilibrium strategies under the Expected Utility Theory (EUT) model become infeasible under PT, and for those Nash Equilibria that are feasible under both EUT and PT, the resulting user utilities are less under PT. We propose resource allocation and bidding mechanisms for the SPs to mitigate these effects.

cs.NI↗

arXiv2018

Robust Deep Reinforcement Learning for Security and Safety in Autonomous Vehicle Systems

To operate effectively in tomorrow's smart cities, autonomous vehicles (AVs) must rely on intra-vehicle sensors such as camera and radar as well as inter-vehicle communication. Such dependence on sensors and communication links exposes AVs to cyber-physical (CP) attacks by adversaries that seek to take control of the AVs by manipulating their data. Thus, to ensure safe and optimal AV dynamics control, the data processing functions at AVs must be robust to such CP attacks. To this end, in this paper, the state estimation process for monitoring AV dynamics, in presence of CP attacks, is analyzed and a novel adversarial deep reinforcement learning (RL) algorithm is proposed to maximize the robustness of AV dynamics control to CP attacks. The attacker's action and the AV's reaction to CP attacks are studied in a game-theoretic framework. In the formulated game, the attacker seeks to inject faulty data to AV sensor readings so as to manipulate the inter-vehicle optimal safe spacing and potentially increase the risk of AV accidents or reduce the vehicle flow on the roads. Meanwhile, the AV, acting as a defender, seeks to minimize the deviations of spacing so as to ensure robustness to the attacker's actions. Since the AV has no information about the attacker's action and due to the infinite possibilities for data value manipulations, the outcome of the players' past interactions are fed to long-short term memory (LSTM) blocks. Each player's LSTM block learns the expected spacing deviation resulting from its own action and feeds it to its RL algorithm. Then, the the attacker's RL algorithm chooses the action which maximizes the spacing deviation, while the AV's RL algorithm tries to find the optimal action that minimizes such deviation.

eess.SY↗