arXiv subjects

Quanyan Zhu

Publications and source records attributed to Quanyan Zhu.

At least 73 records · Page 4Linked to original sources

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

Cloud-Fog Automation: The New Paradigm towards Autonomous Industrial Cyber-Physical Systems

Autonomous Industrial Cyber-Physical Systems (ICPS) represent a future vision where industrial systems achieve full autonomy, integrating physical processes seamlessly with communication, computing and control technologies while holistically embedding intelligence. Cloud-Fog Automation is a new digitalized industrial automation reference architecture that has been recently proposed. This architecture is a fundamental paradigm shift from the traditional International Society of Automation (ISA)-95 model to accelerate the convergence and synergy of communication, computing, and control towards a fully autonomous ICPS. With the deployment of new wireless technologies to enable almost-deterministic ultra-reliable low-latency communications, a joint design of optimal control and computing has become increasingly important in modern ICPS. It is also imperative that system-wide cyber-physical security are critically enforced. Despite recent advancements in the field, there are still significant research gaps and open technical challenges. Therefore, a deliberate rethink in co-designing and synergizing communications, computing, and control (which we term "3C co-design") is required. In this paper, we position Cloud-Fog Automation with 3C co-design as the new paradigm to realize the vision of autonomous ICPS. We articulate the state-of-the-art and future directions in the field, and specifically discuss how goal-oriented communication, virtualization-empowered computing, and Quality of Service (QoS)-aware control can drive Cloud-Fog Automation towards a fully autonomous ICPS, while accounting for system-wide cyber-physical security.

eess.SY↗

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

Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View

Large language models (LLMs) have been shown to face hallucination issues due to the data they trained on often containing human bias; whether this is reflected in the decision-making process of LLM Agents remains under-explored. As LLM Agents are increasingly employed in intricate social environments, a pressing and natural question emerges: Can we utilize LLM Agents' systematic hallucinations to mirror human cognitive biases, thus exhibiting irrational social intelligence? In this paper, we probe the irrational behavior among contemporary LLM Agents by melding practical social science experiments with theoretical insights. Specifically, We propose CogMir, an open-ended Multi-LLM Agents framework that utilizes hallucination properties to assess and enhance LLM Agents' social intelligence through cognitive biases. Experimental results on CogMir subsets show that LLM Agents and humans exhibit high consistency in irrational and prosocial decision-making under uncertain conditions, underscoring the prosociality of LLM Agents as social entities and highlighting the significance of hallucination properties. Additionally, the CogMir framework demonstrates its potential as a valuable platform for encouraging more research into the social intelligence of LLM Agents.

cs.CY↗

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

Transparent Tagging for Strategic Social Nudges on User-Generated Misinformation

Social network platforms (SNP) rely heavily on user-generated content to attract users, yet they have limited control over content provision, which leads to misinformation. As countermeasures, SNPs have implemented policies to notify users by tagging the content and influencing users' responses to the tagged content. The population-level response creates a social nudge to the content provider that encourages it to supply more authentic content. Yet, when designing tags to leverage social nudges, SNP must be cautious about misdetection, which impairs its ability to create social nudges. We establish a Bayesian persuaded branching process to study SNP's tagging policy design under misdetection. Misinformation circulation is modeled by a multi-type branching process, where users are persuaded through tags to give positive/negative comments that influence misinformation spread. When translated into posterior belief space, the SNP's problem is reduced to an equality-constrained optimization, the optimal condition of which is given by the Lagrangian characterization. The key finding is that SNP's optimal policy is transparent tagging, albeit misdetection, which nudges the provider not to generate misinformation.

cs.GT↗

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↗

arXiv2025

Self-Confirming Transformer for Belief-Conditioned Adaptation in Offline Multi-Agent Reinforcement Learning

Offline reinforcement learning (RL) suffers from the distribution shift between the offline dataset and the online environment. In multi-agent RL (MARL), this distribution shift may arise from the nonstationary opponents in the online testing who display distinct behaviors from those recorded in the offline dataset. Hence, the key to the broader deployment of offline MARL is the online adaptation to nonstationary opponents. Recent advances in foundation models, e.g., large language models, have demonstrated the generalization ability of the transformer, an emerging neural network architecture, in sequence modeling, of which offline RL is a special case. One naturally wonders \textit{whether offline-trained transformer-based RL policies adapt to nonstationary opponents online}. We propose a novel auto-regressive training to equip transformer agents with online adaptability based on the idea of self-augmented pre-conditioning. The transformer agent first learns offline to predict the opponent's action based on past observations. When deployed online, such a fictitious opponent play, referred to as the belief, is fed back to the transformer, together with other environmental feedback, to generate future actions conditional on the belief. Motivated by self-confirming equilibrium in game theory, the training loss consists of belief consistency loss, requiring the beliefs to match the opponent's actual actions and best response loss, mandating the agent to behave optimally under the belief. We evaluate the online adaptability of the proposed self-confirming transformer (SCT) in a structured environment, iterated prisoner's dilemma games, to demonstrate SCT's belief consistency and equilibrium behaviors as well as more involved multi-particle environments to showcase its superior performance against nonstationary opponents over prior transformers and offline MARL baselines.

cs.LG↗

arXiv2025

Automated Security Response through Online Learning with Adaptive Conjectures

We study automated security response for an IT infrastructure and formulate the interaction between an attacker and a defender as a partially observed, non-stationary game. We relax the standard assumption that the game model is correctly specified and consider that each player has a probabilistic conjecture about the model, which may be misspecified in the sense that the true model has probability 0. This formulation allows us to capture uncertainty and misconception about the infrastructure and the intents of the players. To learn effective game strategies online, we design Conjectural Online Learning (COL), a novel method where a player iteratively adapts its conjecture using Bayesian learning and updates its strategy through rollout. We prove that the conjectures converge to best fits, and we provide a bound on the performance improvement that rollout enables with a conjectured model. To characterize the steady state of the game, we propose a variant of the Berk-Nash equilibrium. We present COL through an advanced persistent threat use case. Testbed evaluations show that COL produces effective security strategies that adapt to a changing environment. We also find that COL enables faster convergence than current reinforcement learning techniques.

cs.GT↗

arXiv2024

Game-Theoretic Foundations for Cyber Resilience Against Deceptive Information Attacks in Intelligent Transportation Systems

The growing complexity and interconnectivity of Intelligent Transportation Systems (ITS) make them increasingly vulnerable to advanced cyber threats, particularly deceptive information attacks. These sophisticated threats exploit vulnerabilities to manipulate data integrity and decision-making processes through techniques such as data poisoning, spoofing, and phishing. They target multiple ITS domains, including intra-vehicle systems, inter-vehicle communications, transportation infrastructure, and human interactions, creating cascading effects across the ecosystem. This chapter introduces a game-theoretic framework, enhanced by control and learning theories, to systematically analyze and mitigate these risks. By modeling the strategic interactions among attackers, users, and system operators, the framework facilitates comprehensive risk assessment and the design of adaptive, scalable resilience mechanisms. A prime example of this approach is the Proactive Risk Assessment and Mitigation of Misinformed Demand Attacks (PRADA) system, which integrates trust mechanisms, dynamic learning processes, and multi-layered defense strategies to counteract deceptive attacks on navigational recommendation systems. In addition, the chapter explores the broader applicability of these methodologies to address various ITS threats, including spoofing, Advanced Persistent Threats (APTs), and denial-of-service attacks. It highlights cross-domain resilience strategies, offering actionable insights to bolster the security, reliability, and adaptability of ITS. By providing a robust game-theoretic foundation, this work advances the development of comprehensive solutions to the evolving challenges in ITS cybersecurity.

cs.GT↗

arXiv2024

Game-Theoretic Neyman-Pearson Detection to Combat Strategic Evasion

The security in networked systems depends greatly on recognizing and identifying adversarial behaviors. Traditional detection methods focus on specific categories of attacks and have become inadequate for increasingly stealthy and deceptive attacks that are designed to bypass detection strategically. This work aims to develop a holistic theory to countermeasure such evasive attacks. We focus on extending a fundamental class of statistical-based detection methods based on Neyman-Pearson's (NP) hypothesis testing formulation. We propose game-theoretic frameworks to capture the conflicting relationship between a strategic evasive attacker and an evasion-aware NP detector. By analyzing both the equilibrium behaviors of the attacker and the NP detector, we characterize their performance using Equilibrium Receiver-Operational-Characteristic (EROC) curves. We show that the evasion-aware NP detectors outperform the passive ones in the way that the former can act strategically against the attacker's behavior and adaptively modify their decision rules based on the received messages. In addition, we extend our framework to a sequential setting where the user sends out identically distributed messages. We corroborate the analytical results with a case study of anomaly detection.

cs.CR↗

arXiv2024

The Game-Theoretic Symbiosis of Trust and AI in Networked Systems

This chapter explores the symbiotic relationship between Artificial Intelligence (AI) and trust in networked systems, focusing on how these two elements reinforce each other in strategic cybersecurity contexts. AI's capabilities in data processing, learning, and real-time response offer unprecedented support for managing trust in dynamic, complex networks. However, the successful integration of AI also hinges on the trustworthiness of AI systems themselves. Using a game-theoretic framework, this chapter presents approaches to trust evaluation, the strategic role of AI in cybersecurity, and governance frameworks that ensure responsible AI deployment. We investigate how trust, when dynamically managed through AI, can form a resilient security ecosystem. By examining trust as both an AI output and an AI requirement, this chapter sets the foundation for a positive feedback loop where AI enhances network security and the trust placed in AI systems fosters their adoption.

cs.AI↗

arXiv2024

Mean Field Control by Stochastic Koopman Operator via a Spectral Method

Mean field control provides a robust framework for coordinating large-scale populations with complex interactions and has wide applications across diverse fields. However, the inherent nonlinearity and the presence of unknown system dynamics pose significant challenges for developing effective analytic or numerical solutions. There is a pressing need for data-driven methodologies to construct accurate models and facilitate efficient planning and control. To this end, we leverage Koopman operator theory to advance solution methods for mean field control problems. Our approach involves exploring stochastic Koopman operators using spectral analysis techniques. Through Koopman decomposition, we derive a linear model for mean field control problems in a data-driven fashion. Finally, we develop a model predictive control framework to achieve robust control and reduce the computational complexity for mean field control problems, thereby enhancing the efficacy and applicability of mean field control solutions in various domains.

math.OC↗

arXiv2024

Revisiting Game-Theoretic Control in Socio-Technical Networks: Emerging Design Frameworks and Contemporary Applications

Socio-technical networks represent emerging cyber-physical infrastructures that are tightly interwoven with human networks. The coupling between human and technical networks presents significant challenges in managing, controlling, and securing these complex, interdependent systems. This paper investigates game-theoretic frameworks for the design and control of socio-technical networks, with a focus on critical applications such as misinformation management, infrastructure optimization, and resilience in socio-cyber-physical systems (SCPS). Core methodologies, including Stackelberg games, mechanism design, and dynamic game theory, are examined as powerful tools for modeling interactions in hierarchical, multi-agent environments. Key challenges addressed include mitigating human-driven vulnerabilities, managing large-scale system dynamics, and countering adversarial threats. By bridging individual agent behaviors with overarching system goals, this work illustrates how the integration of game theory and control theory can lead to robust, resilient, and adaptive socio-technical networks. This paper highlights the potential of these frameworks to dynamically align decentralized agent actions with system-wide objectives of stability, security, and efficiency.

eess.SY↗

arXiv2024

Digital Twin-Enhanced Wireless Indoor Navigation: Achieving Efficient Environment Sensing with Zero-Shot Reinforcement Learning

Millimeter-wave (mmWave) communication is a vital component of future generations of mobile networks, offering not only high data rates but also precise beams, making it ideal for indoor navigation in complex environments. However, the challenges of multipath propagation and noisy signal measurements in indoor spaces complicate the use of mmWave signals for navigation tasks. Traditional physics-based methods, such as following the angle of arrival (AoA), often fall short in complex scenarios, highlighting the need for more sophisticated approaches. Digital twins, as virtual replicas of physical environments, offer a powerful tool for simulating and optimizing mmWave signal propagation in such settings. By creating detailed, physics-based models of real-world spaces, digital twins enable the training of machine learning algorithms in virtual environments, reducing the costs and limitations of physical testing. Despite their advantages, current machine learning models trained in digital twins often overfit specific virtual environments and require costly retraining when applied to new scenarios. In this paper, we propose a Physics-Informed Reinforcement Learning (PIRL) approach that leverages the physical insights provided by digital twins to shape the reinforcement learning (RL) reward function. By integrating physics-based metrics such as signal strength, AoA, and path reflections into the learning process, PIRL enables efficient learning and improved generalization to new environments without retraining. Our experiments demonstrate that the proposed PIRL, supported by digital twin simulations, outperforms traditional heuristics and standard RL models, achieving zero-shot generalization in unseen environments and offering a cost-effective, scalable solution for wireless indoor navigation.

cs.RO↗

arXiv2024

ADAPT: A Game-Theoretic and Neuro-Symbolic Framework for Automated Distributed Adaptive Penetration Testing

The integration of AI into modern critical infrastructure systems, such as healthcare, has introduced new vulnerabilities that can significantly impact workflow, efficiency, and safety. Additionally, the increased connectivity has made traditional human-driven penetration testing insufficient for assessing risks and developing remediation strategies. Consequently, there is a pressing need for a distributed, adaptive, and efficient automated penetration testing framework that not only identifies vulnerabilities but also provides countermeasures to enhance security posture. This work presents ADAPT, a game-theoretic and neuro-symbolic framework for automated distributed adaptive penetration testing, specifically designed to address the unique cybersecurity challenges of AI-enabled healthcare infrastructure networks. We use a healthcare system case study to illustrate the methodologies within ADAPT. The proposed solution enables a learning-based risk assessment. Numerical experiments are used to demonstrate effective countermeasures against various tactical techniques employed by adversarial AI.

cs.CR↗

arXiv2024

Learning from Response not Preference: A Stackelberg Approach for LLM Detoxification using Non-parallel Data

Text detoxification, a variant of style transfer tasks, finds useful applications in online social media. This work presents a fine-tuning method that only uses non-parallel data to turn large language models (LLM) into a detoxification rewritter. We model the fine-tuning process as a Stackelberg game between an LLM (leader) and a toxicity screener (follower), which is a binary style classifier (toxic or non-toxic). The LLM aims to align its preference according to the screener and generate paraphases passing the screening. The primary challenge of non-parallel data fine-tuning is incomplete preference. In the case of unsuccessful paraphrases, the classifier cannot establish a preference between the input and paraphrase, as they belong to the same toxic style. Hence, preference-alignment fine-tuning methods, such as direct preference optimization (DPO), no longer apply. To address the challenge of incomplete preference, we propose Stackelberg response optimization (SRO), adapted from DPO, to enable the LLM to learn from the follower's response. The gist is that SRO decreases the likelihood of generating the paraphrase if it fails the follower's screening while performing DPO on the pair of the toxic input and its paraphrase when the latter passes the screening. Experiments indicate that the SRO-fine-tunned LLM achieves satisfying performance comparable to state-of-the-art models regarding style accuracy, content similarity, and fluency. The overall detoxification performance surpasses other computing methods and matches the human reference. Additional empirical evidence suggests that SRO is sensitive to the screener's feedback, and a slight perturbation leads to a significant performance drop. We release the code and LLM models at \url{https://github.com/XXXinhong/Detoxification_LLM}.

cs.CL↗

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↗