arXiv subjects

Yunian Pan

Publications and source records attributed to Yunian Pan.

At least 19 recordsLinked to original sources

arXiv2026

A Unified Variational Design of Predictive Mirror Descent in Convex Games under Stochastic Feedback

Mirror descent provides a geometric framework for learning in games, but its last-iterate behavior can fail in weakly stable regimes, where the dynamics may exhibit rotational or recurrent transients. Predictive mirror methods mitigate this issue by modifying the feedback entering the mirror update, yet standard predictive variants are typically introduced algorithmically and analyzed one at a time. This letter gives a variational route to predictive feedback by constructing a stochastic mirror differential game with an auxiliary memory state. Its stage cost couples two Fenchel terms: a strategic term evaluated at a predicted profile and a corrective term driven by realized feedback. The resulting equilibrium feedback induces two-channel predictive mirror dynamics in general mirror geometry. Under local mirror regularity, a quantitative local Bregman growth condition, and bounded Brownian diffusion, we establish finite-horizon local terminal-time bounds in expectation and with high probability, together with an exit-probability estimate for the localization neighborhood. The result provides a unified variational construction of the induced predictive-memory mirror flow together with a local stochastic certificate for last-iterate performance near stable equilibria.

math.OC↗

arXiv2025

Decentralized No-Regret Frequency-Time Scheduling for FMCW Radar Interference Avoidance

Automotive FMCW radars are indispensable to modern ADAS and autonomous-driving systems, but their increasing density has intensified the risk of mutual interference. Existing mitigation techniques, including reactive receiver-side suppression, proactive waveform design, and cooperative scheduling, often face limitations in scalability, reliance on side-channel communication, or degradation of range-Doppler resolution. Building on our earlier work on decentralized Frequency-Domain No-Regret hopping, this paper introduces a unified time-frequency game-theoretic framework that enables radars to adapt across both spectral and temporal resources. We formulate the interference-avoidance problem as a repeated anti-coordination game, in which each radar autonomously updates a mixed strategy over frequency subbands and chirp-level time offsets using regret-minimization dynamics. We show that the proposed Time-Frequency No-Regret Hopping algorithm achieves vanishing external and swap regret, and that the induced empirical play converges to an $\varepsilon$-coarse correlated equilibrium or a correlated equilibrium. Theoretical analysis provides regret bounds in the joint domain, revealing how temporal adaptation implicitly regularizes frequency selection and enhances robustness against asynchronous interference. Numerical experiments with multi-radar scenarios demonstrate substantial improvements in SINR, collision rate, and range-Doppler quality compared with time-frequency random hopping and centralized Nash-based benchmarks.

eess.SY↗

arXiv2025

A Games-in-Games Paradigm for Strategic Hybrid Jump-Diffusions: Hamilton-Jacobi-Isaacs Hierarchy and Spectral Structure

This paper develops a hierarchical games-in-games control architecture for hybrid stochastic systems governed by regime-switching jump-diffusions. We model the interplay between continuous state dynamics and discrete mode transitions as a bilevel differential game: an inner layer solves a robust stochastic control problem within each regime, while a strategic outer layer modulates the transition intensities of the underlying Markov chain. A Dynkin-based analysis yields a system of coupled Hamilton-Jacobi-Isaacs (HJI) equations. We prove that for the class of Linear-Quadratic games and Exponential-Affine games, this hierarchy admits tractable semi-closed form solutions via coupled matrix differential equations. We prove that for the class of Linear-Quadratic games and Exponential-Affine games, this hierarchy admits tractable semi-closed form solutions via coupled matrix differential equations. The framework is demonstrated through a case study on adversarial market microstructure, showing how the outer layer's strategic switching pre-emptively adjusts inventory spreads against latent regime risks, which leads to a hyper-alert equilibrium.

eess.SY↗

arXiv2025

Timing-Aware Two-Player Stochastic Games with Self-Triggered Control

We study self-triggered two-player stochastic games on Piecewise Deterministic Markov Processes (PDMPs) where each agent decides when to observe and which open-loop action to hold. Augmenting the state with clocks and committed controls yields flow regions (both hold) and trigger surfaces (at least one updates). The framework covers both blind simultaneous (Nash) timing and observable sequential (Stackelberg) commitments; the former leads to coupled, intractable QVIs, while the latter admits a nested Hamilton-Jacobi-Bellman quasi-variational inequality and a tractable dynamic-programming decomposition. We outline a computational scheme based on implicit differentiation of the follower's fixed point. A pursuit-evasion example illustrates the strategic timing interaction.

eess.SY↗

arXiv2025

Bayesian Holonic Systems: Equilibrium, Uniqueness, and Computation

This paper addresses the challenge of modeling and control in hierarchical, multi-agent systems, known as holonic systems, where local agent decisions are coupled with global systemic outcomes. We introduce the Bayesian Holonic Equilibrium (BHE), a concept that ensures consistency between agent-level rationality and system-wide emergent behavior. We establish the theoretical soundness of the BHE by showing its existence and, under stronger regularity conditions, its uniqueness. We propose a two-time scale learning algorithm to compute such an equilibrium. This algorithm mirrors the system's structure, with a fast timescale for intra-holon strategy coordination and a slow timescale for inter-holon belief adaptation about external risks. The convergence of the algorithm to the theoretical equilibrium is validated through a numerical experiment on a continuous public good game. This work provides a complete theoretical and algorithmic framework for the principled design and analysis of strategic risk in complex, coupled control systems.

eess.SY↗

arXiv2025

From Texts to Shields: Convergence of Large Language Models and Cybersecurity

This report explores the convergence of large language models (LLMs) and cybersecurity, synthesizing interdisciplinary insights from network security, artificial intelligence, formal methods, and human-centered design. It examines emerging applications of LLMs in software and network security, 5G vulnerability analysis, and generative security engineering. The report highlights the role of agentic LLMs in automating complex tasks, improving operational efficiency, and enabling reasoning-driven security analytics. Socio-technical challenges associated with the deployment of LLMs -- including trust, transparency, and ethical considerations -- can be addressed through strategies such as human-in-the-loop systems, role-specific training, and proactive robustness testing. The report further outlines critical research challenges in ensuring interpretability, safety, and fairness in LLM-based systems, particularly in high-stakes domains. By integrating technical advances with organizational and societal considerations, this report presents a forward-looking research agenda for the secure and effective adoption of LLMs in cybersecurity.

cs.CR↗

arXiv2025

Preference-Centric Route Recommendation: Equilibrium, Learning, and Provable Efficiency

Traditional approaches to modeling and predicting traffic behavior often rely on Wardrop Equilibrium (WE), assuming non-atomic traffic demand and neglecting correlations in individual decisions. However, the growing role of real-time human feedback and adaptive recommendation systems calls for more expressive equilibrium concepts that better capture user preferences and the stochastic nature of routing behavior. In this paper, we introduce a preference-centric route recommendation framework grounded in the concept of Borda Coarse Correlated Equilibrium (BCCE), wherein users have no incentive to deviate from recommended strategies when evaluated by Borda scores-pairwise comparisons encoding user preferences. We develop an adaptive algorithm that learns from dueling feedback and show that it achieves $\mathcal{O}(T^{\frac{2}{3}})$ regret, implying convergence to the BCCE under mild assumptions. We conduct empirical evaluations using a case study to illustrate and justify our theoretical analysis. The results demonstrate the efficacy and practical relevance of our approach.

cs.GT↗

arXiv2025

A Game-Theoretic Approach for High-Resolution Automotive FMCW Radar Interference Avoidance

Nonlinear frequency hopping has emerged as a promising approach for mitigating interference and enhancing range resolution in automotive FMCW radar systems. Achieving an optimal balance between high range-resolution and effective interference mitigation remains challenging, especially without centralized frequency scheduling. This paper presents a game-theoretic framework for interference avoidance, in which each radar operates as an independent player, optimizing its performance through decentralized decision-making. We examine two equilibrium concepts--Nash Equilibrium (NE) and Coarse Correlated Equilibrium (CCE)--as strategies for frequency band allocation, with CCE demonstrating particular effectiveness through regret minimization algorithms. We propose two interference avoidance algorithms: Nash Hopping, a model-based approach, and No-Regret Hopping, a model-free adaptive method. Simulation results indicate that both methods effectively reduce interference and enhance the signal-to-interference-plus-noise ratio (SINR). Notably, No-regret Hopping further optimizes frequency spectrum utilization, achieving improved range resolution compared to Nash Hopping.

eess.SP↗

arXiv2025

Model-Agnostic Meta-Policy Optimization via Zeroth-Order Estimation: A Linear Quadratic Regulator Perspective

Meta-learning has been proposed as a promising machine learning topic in recent years, with important applications to image classification, robotics, computer games, and control systems. In this paper, we study the problem of using meta-learning to deal with uncertainty and heterogeneity in ergodic linear quadratic regulators. We integrate the zeroth-order optimization technique with a typical meta-learning method, proposing an algorithm that omits the estimation of policy Hessian, which applies to tasks of learning a set of heterogeneous but similar linear dynamic systems. The induced meta-objective function inherits important properties of the original cost function when the set of linear dynamic systems are meta-learnable, allowing the algorithm to optimize over a learnable landscape without projection onto the feasible set. We provide stability and convergence guarantees for the exact gradient descent process by analyzing the boundedness and local smoothness of the gradient for the meta-objective, which justify the proposed algorithm with gradient estimation error being small. We provide the sample complexity conditions for these theoretical guarantees, as well as a numerical example at the end to corroborate this perspective.

eess.SY↗

arXiv2024

Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks

Federated learning (FL) is susceptible to a range of security threats. Although various defense mechanisms have been proposed, they are typically non-adaptive and tailored to specific types of attacks, leaving them insufficient in the face of multiple uncertain, unknown, and adaptive attacks employing diverse strategies. This work formulates adversarial federated learning under a mixture of various attacks as a Bayesian Stackelberg Markov game, based on which we propose the meta-Stackelberg defense composed of pre-training and online adaptation. {The gist is to simulate strong attack behavior using reinforcement learning (RL-based attacks) in pre-training and then design meta-RL-based defense to combat diverse and adaptive attacks.} We develop an efficient meta-learning approach to solve the game, leading to a robust and adaptive FL defense. Theoretically, our meta-learning algorithm, meta-Stackelberg learning, provably converges to the first-order $\varepsilon$-meta-equilibrium point in $O(\varepsilon^{-2})$ gradient iterations with $O(\varepsilon^{-4})$ samples per iteration. Experiments show that our meta-Stackelberg framework performs superbly against strong model poisoning and backdoor attacks of uncertain and unknown types.

cs.LG↗

arXiv2024

Model-Agnostic Zeroth-Order Policy Optimization for Meta-Learning of Ergodic Linear Quadratic Regulators

Meta-learning has been proposed as a promising machine learning topic in recent years, with important applications to image classification, robotics, computer games, and control systems. In this paper, we study the problem of using meta-learning to deal with uncertainty and heterogeneity in ergodic linear quadratic regulators. We integrate the zeroth-order optimization technique with a typical meta-learning method, proposing an algorithm that omits the estimation of policy Hessian, which applies to tasks of learning a set of heterogeneous but similar linear dynamic systems. The induced meta-objective function inherits important properties of the original cost function when the set of linear dynamic systems are meta-learnable, allowing the algorithm to optimize over a learnable landscape without projection onto the feasible set. We provide a convergence result for the exact gradient descent process by analyzing the boundedness and smoothness of the gradient for the meta-objective, which justify the proposed algorithm with gradient estimation error being small. We also provide a numerical example to corroborate this perspective.

eess.SY↗

arXiv2024

On the Variational Interpretation of Mirror Play in Monotone Games

Mirror play (MP) is a well-accepted primal-dual multi-agent learning algorithm where all agents simultaneously implement mirror descent in a distributed fashion. The advantage of MP over vanilla gradient play lies in its usage of mirror maps that better exploit the geometry of decision domains. Despite extensive literature dedicated to the asymptotic convergence of MP to equilibrium, the understanding of the finite-time behavior of MP before reaching equilibrium is still rudimentary. To facilitate the study of MP's non-equilibrium performance, this work establishes an equivalence between MP's finite-time primal-dual path (mirror path) in monotone games and the closed-loop Nash equilibrium path of a finite-horizon differential game, referred to as mirror differential game (MDG). Our construction of MDG rests on the Brezis-Ekeland variational principle, and the stage cost functional for MDG is Fenchel coupling between MP's iterates and associated gradient updates. The variational interpretation of mirror path in static games as the equilibrium path in MDG holds in deterministic and stochastic cases. Such a variational interpretation translates the non-equilibrium studies of learning dynamics into a more tractable equilibrium analysis of dynamic games, as demonstrated in a case study on the Cournot game, where MP dynamics corresponds to a linear quadratic game.

cs.GT↗

arXiv2023

Decision-Dominant Strategic Defense Against Lateral Movement for 5G Zero-Trust Multi-Domain Networks

Multi-domain warfare is a military doctrine that leverages capabilities from different domains, including air, land, sea, space, and cyberspace, to create a highly interconnected battle network that is difficult for adversaries to disrupt or defeat. However, the adoption of 5G technologies on battlefields presents new vulnerabilities due to the complexity of interconnections and the diversity of software, hardware, and devices from different supply chains. Therefore, establishing a zero-trust architecture for 5G-enabled networks is crucial for continuous monitoring and fast data analytics to protect against targeted attacks. To address these challenges, we propose a proactive end-to-end security scheme that utilizes a 5G satellite-guided air-ground network. Our approach incorporates a decision-dominant learning-based method that can thwart the lateral movement of adversaries targeting critical assets on the battlefield before they can conduct reconnaissance or gain necessary access or credentials. We demonstrate the effectiveness of our game-theoretic design, which uses a meta-learning framework to enable zero-trust monitoring and decision-dominant defense against attackers in emerging multi-domain battlefield networks.

cs.CR↗

arXiv2023

A First Order Meta Stackelberg Method for Robust Federated Learning

Previous research has shown that federated learning (FL) systems are exposed to an array of security risks. Despite the proposal of several defensive strategies, they tend to be non-adaptive and specific to certain types of attacks, rendering them ineffective against unpredictable or adaptive threats. This work models adversarial federated learning as a Bayesian Stackelberg Markov game (BSMG) to capture the defender's incomplete information of various attack types. We propose meta-Stackelberg learning (meta-SL), a provably efficient meta-learning algorithm, to solve the equilibrium strategy in BSMG, leading to an adaptable FL defense. We demonstrate that meta-SL converges to the first-order $\varepsilon$-equilibrium point in $O(\varepsilon^{-2})$ gradient iterations, with $O(\varepsilon^{-4})$ samples needed per iteration, matching the state of the art. Empirical evidence indicates that our meta-Stackelberg framework performs exceptionally well against potent model poisoning and backdoor attacks of an uncertain nature.

cs.LG↗

arXiv2023

A First Order Meta Stackelberg Method for Robust Federated Learning (Technical Report)

Recent research efforts indicate that federated learning (FL) systems are vulnerable to a variety of security breaches. While numerous defense strategies have been suggested, they are mainly designed to counter specific attack patterns and lack adaptability, rendering them less effective when facing uncertain or adaptive threats. This work models adversarial FL as a Bayesian Stackelberg Markov game (BSMG) between the defender and the attacker to address the lack of adaptability to uncertain adaptive attacks. We further devise an effective meta-learning technique to solve for the Stackelberg equilibrium, leading to a resilient and adaptable defense. The experiment results suggest that our meta-Stackelberg learning approach excels in combating intense model poisoning and backdoor attacks of indeterminate types.

cs.CR↗

arXiv2023

Is Stochastic Mirror Descent Vulnerable to Adversarial Delay Attacks? A Traffic Assignment Resilience Study

\textit{Intelligent Navigation Systems} (INS) are exposed to an increasing number of informational attack vectors, which often intercept through the communication channels between the INS and the transportation network during the data collecting process. To measure the resilience of INS, we use the concept of a Wardrop Non-Equilibrium Solution (WANES), which is characterized by the probabilistic outcome of learning within a bounded number of interactions. By using concentration arguments, we have discovered that any bounded feedback delaying attack only degrades the systematic performance up to order $\tilde{\mathcal{O}}(\sqrt{{d^3}{T^{-1}}})$ along the traffic flow trajectory within the Delayed Mirror Descent (DMD) online-learning framework. This degradation in performance can occur with only mild assumptions imposed. Our result implies that learning-based INS infrastructures can achieve Wardrop Non-equilibrium even when experiencing a certain period of disruption in the information structure. These findings provide valuable insights for designing defense mechanisms against possible jamming attacks across different layers of the transportation ecosystem.

cs.LG↗

arXiv2022

On the Resilience of Traffic Networks under Non-Equilibrium Learning

We investigate the resilience of learning-based \textit{Intelligent Navigation Systems} (INS) to informational flow attacks, which exploit the vulnerabilities of IT infrastructure and manipulate traffic condition data. To this end, we propose the notion of \textit{Wardrop Non-Equilibrium Solution} (WANES), which captures the finite-time behavior of dynamic traffic flow adaptation under a learning process. The proposed non-equilibrium solution, characterized by target sets and measurement functions, evaluates the outcome of learning under a bounded number of rounds of interactions, and it pertains to and generalizes the concept of approximate equilibrium. Leveraging finite-time analysis methods, we discover that under the mirror descent (MD) online-learning framework, the traffic flow trajectory is capable of restoring to the Wardrop non-equilibrium solution after a bounded INS attack. The resulting performance loss is of order $\tilde{\mathcal{O}}(T^β)$ ($-\frac{1}{2} \leq β< 0 )$), with a constant dependent on the size of the traffic network, indicating the resilience of the MD-based INS. We corroborate the results using an evacuation case study on a Sioux-Fall transportation network.

eess.SY↗

arXiv2022

On Poisoned Wardrop Equilibrium in Congestion Games

Recent years have witnessed a growing number of attack vectors against increasingly interconnected traffic networks. Informational attacks have emerged as the prominent ones that aim to poison traffic data, misguide users, and manipulate traffic patterns. To study the impact of this class of attacks, we propose a game-theoretic framework where the attacker, as a Stackelberg leader, falsifies the traffic conditions to change the traffic pattern predicted by the Wardrop traffic equilibrium, achieved by the users, or the followers. The intended shift of the Wardrop equilibrium is a consequence of strategic informational poisoning. Leveraging game-theoretic and sensitivity analysis, we quantify the system-level impact of the attack by characterizing the concept of poisoned Price of Anarchy, which compares the poisoned Wardrop equilibrium and its non-poisoned system optimal counterpart. We use an evacuation case study to show that the Stackelberg equilibrium can be found through a two-time scale zeroth-order learning process and demonstrate the disruptive effects of informational poisoning, indicating a compelling need for defense policies to mitigate such security threats.

cs.GT↗