arXiv subjects

Quanyan Zhu

Publications and source records attributed to Quanyan Zhu.

At least 109 records · Page 6Linked to original sources

arXiv2024

Disentangling Resilience from Robustness: Contextual Dualism, Interactionism, and Game-Theoretic Paradigms

This article explains the distinctions between robustness and resilience in control systems. Resilience confronts a distinct set of challenges, posing new ones for designing controllers for feedback systems, networks, and machines that prioritize resilience over robustness. The concept of resilience is explored through a three-stage model, emphasizing the need for a proactive preparation and automated response to elastic events. A toy model is first used to illustrate the tradeoffs between resilience and robustness. Then, it delves into contextual dualism and interactionism, and introduces game-theoretic paradigms as a unifying framework to consolidate resilience and robustness. The article concludes by discussing the interplay between robustness and resilience, suggesting that a comprehensive theory of resilience and quantification metrics, and formalization through game-theoretic frameworks are necessary. The exploration extends to system-of-systems resilience and various mechanisms, including the integration of AI techniques and non-technical solutions, like cyber insurance, to achieve comprehensive resilience in control systems. As we approach 2030, the systems and control community is at the opportune moment to lay scientific foundations of resilience by bridging feedback control theory, game theory, and learning theory. Resilient control systems will enhance overall quality of life, enable the development of a resilient society, and create a societal-scale impact amid global challenges such as climate change, conflicts, and cyber insecurity.

eess.SY↗

arXiv2024

Stackelberg Game-Theoretic Trajectory Guidance for Multi-Robot Systems with Koopman Operator

Guided trajectory planning involves a leader robot strategically directing a follower robot to collaboratively reach a designated destination. However, this task becomes notably challenging when the leader lacks complete knowledge of the follower's decision-making model. There is a need for learning-based methods to effectively design the cooperative plan. To this end, we develop a Stackelberg game-theoretic approach based on the Koopman operator to address the challenge. We first formulate the guided trajectory planning problem through the lens of a dynamic Stackelberg game. We then leverage Koopman operator theory to acquire a learning-based linear system model that approximates the follower's feedback dynamics. Based on this learned model, the leader devises a collision-free trajectory to guide the follower using receding horizon planning. We use simulations to elaborate on the effectiveness of our approach in generating learning models that accurately predict the follower's multi-step behavior when compared to alternative learning techniques. Moreover, our approach successfully accomplishes the guidance task and notably reduces the leader's planning time to nearly half when contrasted with the model-based baseline method.

cs.RO↗

arXiv2024

Understanding Police Force Resource Allocation using Adversarial Optimal Transport with Incomplete Information

Adversarial optimal transport has been proven useful as a mathematical formulation to model resource allocation problems to maximize the efficiency of transportation with an adversary, who modifies the data. It is often the case, however, that only the adversary knows which nodes are malicious and which are not. In this paper we formulate the problem of seeking adversarial optimal transport into Bayesian games. We construct the concept of Bayesian equilibrium and design a distributed algorithm that achieve those equilibria, making our model applicable to large-scale networks. Keywords: game theory, crime control, Markov games

cs.GT↗

arXiv2024

Integrated Cyber-Physical Resiliency for Power Grids under IoT-Enabled Dynamic Botnet Attacks

The wide adoption of Internet of Things (IoT)-enabled energy devices improves the quality of life, but simultaneously, it enlarges the attack surface of the power grid system. The adversary can gain illegitimate control of a large number of these devices and use them as a means to compromise the physical grid operation, a mechanism known as the IoT botnet attack. This paper aims to improve the resiliency of cyber-physical power grids to such attacks. Specifically, we use an epidemic model to understand the dynamic botnet formation, which facilitates the assessment of the cyber layer vulnerability of the grid. The attacker aims to exploit this vulnerability to enable a successful physical compromise, while the system operator's goal is to ensure a normal operation of the grid by mitigating cyber risks. We develop a cross-layer game-theoretic framework for strategic decision-making to enhance cyber-physical grid resiliency. The cyber-layer game guides the system operator on how to defend against the botnet attacker as the first layer of defense, while the dynamic game strategy at the physical layer further counteracts the adversarial behavior in real time for improved physical resilience. A number of case studies on the IEEE-39 bus system are used to corroborate the devised approach.

eess.SY↗

arXiv2023

Zero Trust for Cyber Resilience

The increased connectivity and potential insider threats make traditional network defense vulnerable. Instead of assuming that everything behind the security perimeter is safe, the zero-trust security model verifies every incoming request before granting access. This chapter draws attention to the cyber resilience within the zero-trust model. We introduce the evolution from traditional perimeter-based security to zero trust and discuss their difference. Two key elements of the zero-trust engine are trust evaluation (TE) and policy engine (PE). We introduce the design of the two components and discuss how their interplay would contribute to cyber resilience. Dynamic game theory and learning are applied as quantitative approaches to achieve automated zero-trust cyber resilience. Several case studies and implementations are introduced to illustrate the benefits of such a security model.

cs.CR↗

arXiv2023

Cyber Insurance for Cyber Resilience

Cyber insurance is a complementary mechanism to further reduce the financial impact on the systems after their effort in defending against cyber attacks and implementing resilience mechanism to maintain the system-level operator even though the attacker is already in the system. This chapter presents a review of the quantitative cyber insurance design framework that takes into account the incentives as well as the perceptual aspects of multiple parties. The design framework builds on the correlation between state-of-the-art attacker vectors and defense mechanisms. In particular, we propose the notion of residual risks to characterize the goal of cyber insurance design. By elaborating the insurer's observations necessary for the modeling of the cyber insurance contract, we make comparison between the design strategies of the insurer under scenarios with different monitoring rules. These distinct but practical scenarios give rise to the concept of the intensity of the moral hazard issue. Using the modern techniques in quantifying the risk preferences of individuals, we link the economic impacts of perception manipulation with moral hazard. With the joint design of cyber insurance design and risk perceptions, cyber resilience can be enhanced under mild assumptions on the monitoring of insurees' actions. Finally, we discuss possible extensions on the cyber insurance design framework to more sophisticated settings and the regulations to strengthen the cyber insurance markets.

cs.CR↗

arXiv2023

On the Price of Transparency: A Comparison between Overt Persuasion and Covert Signaling

Transparency of information disclosure has always been considered an instrumental component of effective governance, accountability, and ethical behavior in any organization or system. However, a natural question follows: \emph{what is the cost or benefit of being transparent}, as one may suspect that transparency imposes additional constraints on the information structure, decreasing the maneuverability of the information provider. This work proposes and quantitatively investigates the \emph{price of transparency} (PoT) in strategic information disclosure by comparing the perfect Bayesian equilibrium payoffs under two representative information structures: overt persuasion and covert signaling models. PoT is defined as the ratio between the payoff outcomes in covert and overt interactions. As the main contribution, this work develops a bilevel-bilinear programming approach, called $Z$-programming, to solve for non-degenerate perfect Bayesian equilibria of dynamic incomplete information games with finite states and actions. Using $Z$-programming, we show that it is always in the information provider's interest to choose the transparent information structure, as $0\leq \textrm{PoT}\leq 1$. The upper bound is attainable for any strictly Bayesian-posterior competitive games, of which zero-sum games are a particular case. For continuous games, the PoT, still upper-bounded by $1$, can be arbitrarily close to $0$, indicating the tightness of the lower bound. This tight lower bound suggests that the lack of transparency can result in significant loss for the provider. We corroborate our findings using quadratic games and numerical examples.

cs.GT↗

arXiv2023

Stackelberg Risk Preference Design

Risk measures are commonly used to capture the risk preferences of decision-makers (DMs). The decisions of DMs can be nudged or manipulated when their risk preferences are influenced by factors such as the availability of information about the uncertainties. This work proposes a Stackelberg risk preference design (STRIPE) problem to capture a designer's incentive to influence DMs' risk preferences. STRIPE consists of two levels. In the lower level, individual DMs in a population, known as the followers, respond to uncertainties according to their risk preference types. In the upper level, the leader influences the distribution of the types to induce targeted decisions and steers the follower's preferences to it. Our analysis centers around the solution concept of approximate Stackelberg equilibrium that yields suboptimal behaviors of the players. We show the existence of the approximate Stackelberg equilibrium. The primitive risk perception gap, defined as the Wasserstein distance between the original and the target type distributions, is important in estimating the optimal design cost. We connect the leader's optimality compromise on the cost with her ambiguity tolerance on the follower's approximate solutions leveraging Lipschitzian properties of the lower level solution mapping. To obtain the Stackelberg equilibrium, we reformulate STRIPE into a single-level optimization problem using the spectral representations of law-invariant coherent risk measures. We create a data-driven approach for computation and study its performance guarantees. We apply STRIPE to contract design problems under approximate incentive compatibility. Moreover, we connect STRIPE with meta-learning problems and derive adaptation performance estimates of the meta-parameters.

math.OC↗

arXiv2023

Detection in Human-sensor Systems under Quantum Prospect Theory using Bayesian Persuasion Frameworks

Human-sensor systems have a wide range of applications in fields such as robotics, healthcare, and finance. These systems utilize sensors to observe the true state of nature and generate strategically designed signals, aiding humans in making more accurate decisions regarding the state of nature. We adopt a Bayesian persuasion framework that is integrated with quantum prospect theories. In this framework, we develop a detection scheme where humans aim to determine the true state by observing the realization of quantum states from the sensor. We derive the optimal signaling rule for the sensor and the optimal decision rule for humans. We discover that this scenario violates the total law of probability. Furthermore, we examine how the concepts of rationality can influence the human detection performance and the signaling rules employed by the sensor.

eess.SP↗

arXiv2023

ZETAR: Modeling and Computational Design of Strategic and Adaptive Compliance Policies

Compliance management plays an important role in mitigating insider threats. Incentive design is a proactive and non-invasive approach to achieving compliance by aligning an insider's incentive with the defender's security objective, which motivates (rather than commands) an insider to act in the organization's interests. Controlling insiders' incentives for population-level compliance is challenging because they are neither precisely known nor directly controllable. To this end, we develop ZETAR, a zero-trust audit and recommendation framework, to provide a quantitative approach to model insiders' incentives and design customized recommendation policies to improve their compliance. We formulate primal and dual convex programs to compute the optimal bespoke recommendation policies. We create the theoretical underpinning for understanding trust, compliance, and satisfaction, which leads to scoring mechanisms of how compliant and persuadable an insider is. After classifying insiders as malicious, self-interested, or amenable based on their incentive misalignment levels with the defender, we establish bespoke information disclosure principles for these insiders of different incentive categories. We identify the policy separability principle and the set convexity, which enable finite-step algorithms to efficiently learn the Completely Trustworthy (CT) policy set when insiders' incentives are unknown. Finally, we present a case study to corroborate the design. Our results show that ZETAR can well adapt to insiders with different risk and compliance attitudes and significantly improve compliance. Moreover, trustworthy recommendations can provably promote cyber hygiene and insiders' satisfaction.

cs.GT↗

arXiv2023

Stochastic Game with Interactive Information Acquisition: Pipelined Perfect Markov Bayesian Equilibrium

This paper studies a multi-player, general-sum stochastic game characterized by a dual-stage temporal structure per period. The agents face uncertainty regarding the time-evolving state that is realized at the beginning of each period. During the first stage, agents engage in information acquisition regarding the unknown state. Each agent strategically selects from multiple signaling options, each carrying a distinct cost. The selected signaling rule dispenses private information that determines the type of the agent. In the second stage, the agents play a Bayesian game by taking actions contingent on their private types. We introduce an equilibrium concept, Pipelined Perfect Markov Bayesian Equilibrium (PPME), which incorporates the Markov perfect equilibrium and the perfect Bayesian equilibrium. We propose a novel equilibrium characterization principle termed fixed-point alignment and deliver a set of verifiable necessary and sufficient conditions for any strategy profile to achieve PPME.

cs.GT↗

arXiv2023

Strategic Information Attacks on Incentive-Compatible Navigational Recommendations in Intelligent Transportation Systems

Intelligent transportation systems (ITS) have gained significant attention from various communities, driven by rapid advancements in informational technology. Within the realm of ITS, navigational recommendation systems (RS) play a pivotal role, as users often face diverse path (route) options in such complex urban environments. However, RS is not immune to vulnerabilities, especially when confronted with potential information-based attacks. This study aims to explore the impacts of these cyber threats on RS, explicitly focusing on local targeted information attacks in which the attacker favors certain groups or businesses. We study human behaviors and propose the coordinated incentive-compatible RS that guides users toward a mixed Nash equilibrium, under which each user has no incentive to deviate from the recommendation. Then, we delve into the vulnerabilities within the recommendation process, focusing on scenarios involving misinformed demands. In such cases, the attacker can fabricate fake users to mislead the RS's recommendations. Using the Stackelberg game approach, the analytical results and the numerical case study reveal that RS is susceptible to informational attacks. This study highlights the need to consider informational attacks for a more resilient and effective navigational recommendation.

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

Game of Travesty: Decoy-based Psychological Cyber Deception for Proactive Human Agents

The concept of cyber deception has been receiving emerging attention. The development of cyber defensive deception techniques requires interdisciplinary work, among which cognitive science plays an important role. In this work, we adopt a signaling game framework between a defender and a human agent to develop a cyber defensive deception protocol that takes advantage of the cognitive biases of human decision-making using quantum decision theory to combat insider attacks (IA). The defender deceives an inside human attacker by luring him to access decoy sensors via generators producing perceptions of classical signals to manipulate the human attacker's psychological state of mind. Our results reveal that even without changing the classical traffic data, strategically designed generators can result in a worse performance for defending against insider attackers in identifying decoys than the ones in the deceptive scheme without generators, which generate random information based on input signals. The proposed framework leads to fundamental theories in designing more effective signaling schemes.

cs.CR↗

arXiv2023

Neurosymbolic Meta-Reinforcement Lookahead Learning Achieves Safe Self-Driving in Non-Stationary Environments

In the area of learning-driven artificial intelligence advancement, the integration of machine learning (ML) into self-driving (SD) technology stands as an impressive engineering feat. Yet, in real-world applications outside the confines of controlled laboratory scenarios, the deployment of self-driving technology assumes a life-critical role, necessitating heightened attention from researchers towards both safety and efficiency. To illustrate, when a self-driving model encounters an unfamiliar environment in real-time execution, the focus must not solely revolve around enhancing its anticipated performance; equal consideration must be given to ensuring its execution or real-time adaptation maintains a requisite level of safety. This study introduces an algorithm for online meta-reinforcement learning, employing lookahead symbolic constraints based on \emph{Neurosymbolic Meta-Reinforcement Lookahead Learning} (NUMERLA). NUMERLA proposes a lookahead updating mechanism that harmonizes the efficiency of online adaptations with the overarching goal of ensuring long-term safety. Experimental results demonstrate NUMERLA confers the self-driving agent with the capacity for real-time adaptability, leading to safe and self-adaptive driving under non-stationary urban human-vehicle interaction scenarios.

cs.RO↗

arXiv2023

The Confluence of Networks, Games and Learning

Recent years have witnessed significant advances in technologies and services in modern network applications, including smart grid management, wireless communication, cybersecurity as well as multi-agent autonomous systems. Considering the heterogeneous nature of networked entities, emerging network applications call for game-theoretic models and learning-based approaches in order to create distributed network intelligence that responds to uncertainties and disruptions in a dynamic or an adversarial environment. This paper articulates the confluence of networks, games and learning, which establishes a theoretical underpinning for understanding multi-agent decision-making over networks. We provide an selective overview of game-theoretic learning algorithms within the framework of stochastic approximation theory, and associated applications in some representative contexts of modern network systems, such as the next generation wireless communication networks, the smart grid and distributed machine learning. In addition to existing research works on game-theoretic learning over networks, we highlight several new angles and research endeavors on learning in games that are related to recent developments in artificial intelligence. Some of the new angles extrapolate from our own research interests. The overall objective of the paper is to provide the reader a clear picture of the strengths and challenges of adopting game-theoretic learning methods within the context of network systems, and further to identify fruitful future research directions on both theoretical and applied studies.

cs.MA↗

arXiv2023

Commitment with Signaling under Double-sided Information Asymmetry

Information asymmetry in games enables players with the information advantage to manipulate others' beliefs by strategically revealing information to other players. This work considers a double-sided information asymmetry in a Bayesian Stackelberg game, where the leader's realized action, sampled from the mixed strategy commitment, is hidden from the follower. In contrast, the follower holds private information about his payoff. Given asymmetric information on both sides, an important question arises: \emph{Does the leader's information advantage outweigh the follower's?} We answer this question affirmatively in this work, where we demonstrate that by adequately designing a signaling device that reveals partial information regarding the leader's realized action to the follower, the leader can achieve a higher expected utility than that without signaling. Moreover, unlike previous works on the Bayesian Stackelberg game where mathematical programming tools are utilized, we interpret the leader's commitment as a probability measure over the belief space. Such a probabilistic language greatly simplifies the analysis and allows an indirect signaling scheme, leading to a geometric characterization of the equilibrium under the proposed game model.

cs.GT↗

arXiv2023

Designing Policies for Truth: Combating Misinformation with Transparency and Information Design

Misinformation has become a growing issue on online social platforms (OSPs), especially during elections or pandemics. To combat this, OSPs have implemented various policies, such as tagging, to notify users about potentially misleading information. However, these policies are often transparent and therefore susceptible to being exploited by content creators, who may not be willing to invest effort into producing authentic content, causing the viral spread of misinformation. Instead of mitigating the reach of existing misinformation, this work focuses on a solution of prevention, aiming to stop the spread of misinformation before it has a chance to gain momentum. We propose a Bayesian persuaded branching process ($\operatorname{BP}^2$) to model the strategic interactions among the OSP, the content creator, and the user. The misinformation spread on OSP is modeled by a multi-type branching process, where users' positive and negative comments influence the misinformation spreading. Using a Lagrangian induced by Bayesian plausibility, we characterize the OSP's optimal policy under the perfect Bayesian equilibrium. The convexity of the Lagrangian implies that the OSP's optimal policy is simply the fully informative tagging policy: revealing the content's accuracy to the user. Such a tagging policy solicits the best effort from the content creator in reducing misinformation, even though the OSP exerts no direct control over the content creator. We corroborate our findings using numerical simulations.

cs.GT↗