Visible to the public Biblio

Filters: Author is Zhu, Quanyan  [Clear All Filters]
2023-01-13
Ge, Yunfei, Zhu, Quanyan.  2022.  Trust Threshold Policy for Explainable and Adaptive Zero-Trust Defense in Enterprise Networks. 2022 IEEE Conference on Communications and Network Security (CNS). :359–364.
In response to the vulnerabilities in traditional perimeter-based network security, the zero trust framework is a promising approach to secure modern network systems and address the challenges. The core of zero trust security is agent-centric trust evaluation and trust-based security decisions. The challenges, however, arise from the limited observations of the agent's footprint and asymmetric information in the decision-making. An effective trust policy needs to tradeoff between the security and usability of the network. The explainability of the policy facilitates the human understanding of the policy, the trust of the result, as well as the adoption of the technology. To this end, we formulate a zero-trust defense model using Partially Observable Markov Decision Processes (POMDP), which captures the uncertainties in the observations of the defender. The framework leads to an explainable trust-threshold policy that determines the defense policy based on the trust scores. This policy is shown to achieve optimal performance under mild conditions. The trust threshold enables an efficient algorithm to compute the defense policy while providing online learning capabilities. We use an enterprise network as a case study to corroborate the results. We discuss key factors on the trust threshold and illustrate how the trust threshold policy can adapt to different environments.
2022-09-09
Kieras, Timothy, Farooq, Muhammad Junaid, Zhu, Quanyan.  2020.  RIoTS: Risk Analysis of IoT Supply Chain Threats. 2020 IEEE 6th World Forum on Internet of Things (WF-IoT). :1—6.
Securing the supply chain of information and communications technology (ICT) has recently emerged as a critical concern for national security and integrity. With the proliferation of Internet of Things (IoT) devices and their increasing role in controlling real world infrastructure, there is a need to analyze risks in networked systems beyond established security analyses. Existing methods in literature typically leverage attack and fault trees to analyze malicious activity and its impact. In this paper, we develop RIoTS, a security risk assessment framework borrowing from system reliability theory to incorporate the supply chain. We also analyze the impact of grouping within suppliers that may pose hidden risks to the systems from malicious supply chain actors. The results show that the proposed analysis is able to reveal hidden threats posed to the IoT ecosystem from potential supplier collusion.
Kieras, Timothy, Farooq, Muhammad Junaid, Zhu, Quanyan.  2020.  Modeling and Assessment of IoT Supply Chain Security Risks: The Role of Structural and Parametric Uncertainties. 2020 IEEE Security and Privacy Workshops (SPW). :163—170.

Supply chain security threats pose new challenges to security risk modeling techniques for complex ICT systems such as the IoT. With established techniques drawn from attack trees and reliability analysis providing needed points of reference, graph-based analysis can provide a framework for considering the role of suppliers in such systems. We present such a framework here while highlighting the need for a component-centered model. Given resource limitations when applying this model to existing systems, we study various classes of uncertainties in model development, including structural uncertainties and uncertainties in the magnitude of estimated event probabilities. Using case studies, we find that structural uncertainties constitute a greater challenge to model utility and as such should receive particular attention. Best practices in the face of these uncertainties are proposed.

2022-04-19
Huang, Yunhan, Xiong, Zehui, Zhu, Quanyan.  2021.  Cross-Layer Coordinated Attacks on Cyber-Physical Systems: A LQG Game Framework with Controlled Observations. 2021 European Control Conference (ECC). :521–528.
This work establishes a game-theoretic framework to study cross-layer coordinated attacks on cyber-physical systems (CPSs). The attacker can interfere with the physical process and launch jamming attacks on the communication channels simultaneously. At the same time, the defender can dodge the jamming by dispensing with observations. The generic framework captures a wide variety of classic attack models on CPSs. Leveraging dynamic programming techniques, we fully characterize the Subgame Perfect Equilibrium (SPE) control strategies. We also derive the SPE observation and jamming strategies and provide efficient computational methods to compute them. The results demonstrate that the physical and cyber attacks are coordinated and depend on each other.On the one hand, the control strategies are linear in the state estimate, and the estimate error caused by jamming attacks will induce performance degradation. On the other hand, the interactions between the attacker and the defender in the physical layer significantly impact the observation and jamming strategies. Numerical examples illustrate the inter-actions between the defender and the attacker through their observation and jamming strategies.
2021-08-11
Chen, Juntao, Touati, Corinne, Zhu, Quanyan.  2020.  Optimal Secure Two-Layer IoT Network Design. IEEE Transactions on Control of Network Systems. 7:398–409.
With the remarkable growth of the Internet and communication technologies over the past few decades, Internet of Things (IoTs) is enabling the ubiquitous connectivity of heterogeneous physical devices with software, sensors, and actuators. IoT networks are naturally two layers with the cloud and cellular networks coexisting with the underlaid device-to-device communications. The connectivity of IoTs plays an important role in information dissemination for mission-critical and civilian applications. However, IoT communication networks are vulnerable to cyber attacks including the denial-of-service and jamming attacks, resulting in link removals in the IoT network. In this paper, we develop a heterogeneous IoT network design framework in which a network designer can add links to provide additional communication paths between two nodes or secure links against attacks by investing resources. By anticipating the strategic cyber attacks, we characterize the optimal design of the secure IoT network by first providing a lower bound on the number of links a secure network requires for a given budget of protected links, and then developing a method to construct networks that satisfy the heterogeneous network design specifications. Therefore, each layer of the designed heterogeneous IoT network is resistant to a predefined level of malicious attacks with minimum resources. Finally, we provide case studies on the Internet of Battlefield Things to corroborate and illustrate our obtained results.
2020-08-07
Pawlick, Jeffrey, Nguyen, Thi Thu Hang, Colbert, Edward, Zhu, Quanyan.  2019.  Optimal Timing in Dynamic and Robust Attacker Engagement During Advanced Persistent Threats. 2019 International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT). :1—8.
Advanced persistent threats (APTs) are stealthy attacks which make use of social engineering and deception to give adversaries insider access to networked systems. Against APTs, active defense technologies aim to create and exploit information asymmetry for defenders. In this paper, we study a scenario in which a powerful defender uses honeynets for active defense in order to observe an attacker who has penetrated the network. Rather than immediately eject the attacker, the defender may elect to gather information. We introduce an undiscounted, infinite-horizon Markov decision process on a continuous state space in order to model the defender's problem. We find a threshold of information that the defender should gather about the attacker before ejecting him. Then we study the robustness of this policy using a Stackelberg game. Finally, we simulate the policy for a conceptual network. Our results provide a quantitative foundation for studying optimal timing for attacker engagement in network defense.
2018-10-26
Xu, Zhiheng, Zhu, Quanyan.  2017.  A Game-Theoretic Approach to Secure Control of Communication-Based Train Control Systems Under Jamming Attacks. Proceedings of the 1st International Workshop on Safe Control of Connected and Autonomous Vehicles. :27–34.

To meet the growing railway-transportation demand, a new train control system, communication-based train control (CBTC) system, aims to maximize the ability of train lines by reducing the headway of each train. However, the wireless communications expose the CBTC system to new security threats. Due to the cyber-physical nature of the CBTC system, a jamming attack can damage the physical part of the train system by disrupting the communications. To address this issue, we develop a secure framework to mitigate the impact of the jamming attack based on a security criterion. At the cyber layer, we apply a multi-channel model to enhance the reliability of the communications and develop a zero-sum stochastic game to capture the interactions between the transmitter and jammer. We present analytical results and apply dynamic programming to find the equilibrium of the stochastic game. Finally, the experimental results are provided to evaluate the performance of the proposed secure mechanism.

2018-05-01
Wang, Weiyu, Zhu, Quanyan.  2017.  On the Detection of Adversarial Attacks Against Deep Neural Networks. Proceedings of the 2017 Workshop on Automated Decision Making for Active Cyber Defense. :27–30.

Deep learning model has been widely studied and proven to achieve high accuracy in various pattern recognition tasks, especially in image recognition. However, due to its non-linear architecture and high-dimensional inputs, its ill-posedness [1] towards adversarial perturbations-small deliberately crafted perturbations on the input will lead to completely different outputs, has also attracted researchers' attention. This work takes the traffic sign recognition system on the self-driving car as an example, and aims at designing an additional mechanism to improve the robustness of the recognition system. It uses a machine learning model which learns the results of the deep learning model's predictions, with human feedback as labels and provides the credibility of current prediction. The mechanism makes use of both the input image and the recognition result as sample space, querying a human user the True/False of current classification result the least number of times, and completing the task of detecting adversarial attacks.