Cyber-physical systems (CPS) have experienced rapid growth in recent decades. However, like any other computer-based systems, malicious attacks evolve mutually, driving CPS to undesirable physical states and potentially causing catastrophes. Although the current state-of-the-art is well aware of this issue, the majority of researchers have not focused on CPS recovery, the procedure we defined as restoring a CPS’s physical state back to a target condition under adversarial attacks. To call for attention on CPS recovery and identify existing efforts, we have surveyed a total of 30 relevant papers. We identify a major partition of the proposed recovery strategies: shallow recovery vs. deep recovery, where the former does not use a dedicated recovery controller while the latter does. Additionally, we surveyed exploratory research on topics that facilitate recovery. From these publications, we discuss the current state-of-the-art of CPS recovery, with respect to applications, attack type, attack surfaces and system dynamics. Then, we identify untouched sub-domains in this field and suggest possible future directions for researchers.
@article{10.1145/3653974,series={CS},keywords={jour},author={Lu, Pengyuan and Zhang, Lin and Liu, Mengyu and Sridhar, Kaustubh and Sokolsky, Oleg and Kong, Fanxin and Lee, Insup},author+an={2=highlight},title={Recovery from Adversarial Attacks in Cyber-physical Systems: Shallow, Deep and Exploratory Works},year={2024},publisher={Association for Computing Machinery},address={New York, NY, USA},issn={0360-0300},url={https://doi.org/10.1145/3653974},doi={10.1145/3653974},note={Just Accepted},journal={ACM Comput. Surv.},month=mar}
TECS ’23
Optimal Checkpointing Strategy for Real-Time Systems with Both Logical and Timing Correctness
Real-time systems are susceptible to adversarial factors such as faults and attacks, leading to severe consequences. This paper presents an optimal checkpoint scheme to bolster fault resilience in real-time systems, addressing both logical consistency and timing correctness. First, we partition message-passing processes into a directed acyclic graph (DAG) based on their dependencies, ensuring checkpoint logical consistency. Then, we identify the DAG’s critical path, representing the longest sequential path, and analyze the optimal checkpoint strategy along this path to minimize overall execution time, including checkpointing overhead. Upon fault detection, the system rolls back to the nearest valid checkpoints for recovery. Our algorithm derives the optimal checkpoint count and intervals, and we evaluate its performance through extensive simulations and a case study. Results show a 99.97% and 67.86% reduction in execution time compared to checkpoint-free systems in simulations and the case study, respectively. Moreover, our proposed strategy outperforms prior work and baseline methods, increasing deadline achievement rates by 31.41% and 2.92% for small-scale tasks and 78.53% and 4.15% for large-scale tasks.
@article{zhang2023optimal,series={TECS '23},keywords={jour},author={Zhang, Lin and Wang, Zifan and Kong, Fanxin},author+an={1=highlight,first; 2=first},title={Optimal Checkpointing Strategy for Real-Time Systems with Both Logical and Timing Correctness},year={2023},issue_date={July 2023},publisher={Association for Computing Machinery},address={New York, NY, USA},volume={22},number={4},issn={1539-9087},url={https://doi.org/10.1145/3603172},doi={10.1145/3603172},journal={ACM Trans. Embed. Comput. Syst.},month=jul,articleno={66},numpages={21}}
TECS ’22
Attack-Resilient Fusion of Sensor Data with Uncertain Delays
Yanfeng Chen, Tianyu Zhang, Fanxin Kong,
Lin Zhang, and Qingxu Deng
Malicious attackers may disrupt the safety of autonomous systems through compromising sensors to feed wrong measurements to the controller. This paper proposes attack-resilient sensor fusion that combines local sensor readings and shared sensing information from multiple sources. The method results in higher resilience against sensor attacks through jointly considering sensing noise and uncertain communication delay. To be specific, we first identify the considerable impact of the delay on determining attacked sensors. Second, we present a novel two-dimensional abstract sensor model, where each measurement is augmented as a probabilistic interval based on the convolution of the noise and delay. Third, we propose a fusion algorithm that admits the fused value with highest joint probability distribution of the intervals to tolerate corrupted measurements. Finally, we demonstrate the effectiveness of our method in a vehicle-platoon case study using extensive simulations and testbed experiments.
@article{chen2022attack,series={TECS '22},keywords={jour},author={Chen, Yanfeng and Zhang, Tianyu and Kong, Fanxin and Zhang, Lin and Deng, Qingxu},author+an={4=highlight},title={Attack-Resilient Fusion of Sensor Data with Uncertain Delays},year={2022},publisher={Association for Computing Machinery},address={New York, NY, USA},issn={1539-9087},url={https://doi.org/10.1145/3532181},doi={10.1145/3532181},journal={ACM Trans. Embed. Comput. Syst.},month=mar}
EMSOFT ’21
Real-Time Attack-Recovery for Cyber-Physical Systems Using Linear-Quadratic Regulator
The increasing autonomy and connectivity in cyber-physical systems (CPS) come with new security vulnerabilities that are easily exploitable by malicious attackers to spoof a system to perform dangerous actions. While the vast majority of existing works focus on attack prevention and detection, the key question is “what to do after detecting an attack?”. This problem attracts fairly rare attention though its significance is emphasized by the need to mitigate or even eliminate attack impacts on a system. In this article, we study this attack response problem and propose novel real-time recovery for securing CPS. First, this work’s core component is a recovery control calculator using a Linear-Quadratic Regulator (LQR) with timing and safety constraints. This component can smoothly steer back a physical system under control to a target state set before a safe deadline and maintain the system state in the set once it is driven to it. We further propose an Alternating Direction Method of Multipliers (ADMM) based algorithm that can fast solve the LQR-based recovery problem. Second, supporting components for the attack recovery computation include a checkpointer, a state reconstructor, and a deadline estimator. To realize these components respectively, we propose (i) a sliding-window-based checkpointing protocol that governs sufficient trustworthy data, (ii) a state reconstruction approach that uses the checkpointed data to estimate the current system state, and (iii) a reachability-based approach to conservatively estimate a safe deadline. Finally, we implement our approach and demonstrate its effectiveness in dealing with totally 15 experimental scenarios which are designed based on 5 CPS simulators and 3 types of sensor attacks.
@article{zhang2021realtime,series={EMSOFT '21},keywords={jour},author={Zhang, Lin and Lu, Pengyuan and Kong, Fanxin and Chen, Xin and Sokolsky, Oleg and Lee, Insup},author+an={1=highlight},title={Real-Time Attack-Recovery for Cyber-Physical Systems Using Linear-Quadratic Regulator},year={2021},issue_date={October 2021},publisher={Association for Computing Machinery},address={New York, NY, USA},volume={20},number={5s},issn={1539-9087},url={https://doi.org/10.1145/3477010},doi={10.1145/3477010},journal={ACM Trans. Embed. Comput. Syst.},month=sep,articleno={79},numpages={24}}
Refereed Conference Proceedings
RTAS ’24
Fast Attack Recovery for Stochastic Cyber-Physical Systems
Cyber-physical systems tightly integrate computational resources with physical processes through sensing and actuating, widely penetrating various safety-critical domains, such as autonomous driving, medical monitoring, and industrial control. Unfortunately, they are susceptible to assorted attacks that result in injuries or physical damage soon after the system is compromised. Consequently, we require mechanisms that swiftly recover their physical states, redirecting a compromised system to desired states to mitigate hazardous situations. However, existing recovery studies have overlooked stochastic uncertainties that can be unbounded, making a recovery infeasible or invalidating safety and real-time guarantees. This paper presents a novel recovery approach that achieves the highest probability of steering the physical states of systems with stochastic uncertainties to a target set rapidly or within a given time. Further, we prove that our method is sound, complete, fast, and has low computational complexity if the target set can be expressed as a strip. Finally, we demonstrate the practicality of our solution through the implementation in multiple use cases encompassing both linear and nonlinear dynamics, including robotic vehicles, drones, and vehicles in high-fidelity simulators.
@inproceedings{zhang2024fast,series={RTAS '24},keywords={conf},author={Zhang, Lin and Burbano, Luis and Chen, Xin and Cardenas, Alvaro A. and Drager, Steve and Anderson, Matthew and Kong, Fanxin},author+an={1=highlight,first; 2=first},booktitle={2024 IEEE 30th Real-Time and Embedded Technology and Applications Symposium (RTAS)},title={Fast Attack Recovery for Stochastic Cyber-Physical Systems},year={2024}}
RTAS ’23
Real-Time Data-Predictive Attack-Recovery for Complex Cyber-Physical Systems
Cyber-physical systems (CPSs) leverage computations to operate physical objects in real-world environments, and increasingly more CPS-based applications have been designed for life-critical applications. Therefore, any vulnerability in such a system can lead to severe consequences if exploited by adversaries. In this paper, we present a data predictive recovery system to safeguard the CPS from sensor attacks, assuming that we can identify compromised sensors from data. Our recovery system guarantees that the CPS will never encounter unsafe states and will smoothly recover to a target set within a conservative deadline. It also guarantees that the CPS will remain within the target set for a specified period. Major highlights of our paper include (i) the recovery procedure works on nonlinear systems, (ii) the method leverages uncorrupted sensors to relieve uncertainty accumulation, and (iii) an extensive set of experiments on various nonlinear benchmarks that demonstrate our framework’s performance and efficiency.
@inproceedings{zhang2023realtime,series={RTAS '23},keywords={conf},author={Zhang, Lin and Sridhar, Kaustubh and Liu, Mengyu and Lu, Pengyuan and Chen, Xin and Kong, Fanxin and Sokolsky, Oleg and Lee, Insup},author+an={1=highlight},booktitle={2023 IEEE 29th Real-Time and Embedded Technology and Applications Symposium (RTAS)},title={Real-Time Data-Predictive Attack-Recovery for Complex Cyber-Physical Systems},year={2023},volume={},number={},pages={209-222},doi={10.1109/RTAS58335.2023.00024}}
RTSS ’23
Learn-to-Respond: Sequence-Predictive Recovery from Sensor Attacks in Cyber-Physical Systems
Mengyu Liu,
Lin Zhang, Vir V. Phoha, and Fanxin Kong
In 2023 IEEE Real-Time Systems Symposium (RTSS), 2023
While many research efforts on Cyber-Physical System (CPS) security are devoted to attack detection, how to respond to the detected attacks receives little attention. Attack response is essential since serious consequences can be caused if CPS continues to act on the compromised data by the attacks. In this work, we aim at the response to sensor attacks and adapt machine learning techniques to recover CPSs from such attacks. There are, however, several major challenges. i) Cumulative error. Recovery needs to estimate the current state of a physical system (e.g., the speed of a vehicle) in order to know if the system has been driven to a certain state. However, the estimation error accumulates over time in presence of compromised sensors. ii) Timely response. A fast response is needed since slow recovery not only comes with large estimation errors but also may be too late to avoid irreparable consequences. To address these challenges, we propose a novel learning-based solution, named sequence-predictive recovery (or SeqRec). To reduce the estimation error, SeqRec designs the first sequence-to-sequence (Seq2Seq) model to uncover the temporal and spatial dependencies among sensors and control demands, and then uses the model to estimate system states using the trustworthy data logged in history. To achieve an adequate and fast recovery, SeqRec designs the second Seq2Seq model that considers both the current time step using the remaining intact sensors and the future time steps based on a given target state, and embeds the model into a novel recovery control algorithm to drive a physical system back to that state. Experimental results demonstrate that SeqRec can effectively and efficiently recover CPSs from sensor attacks.
@inproceedings{liu2023learn,series={RTSS '23},keywords={conf},author={Liu, Mengyu and Zhang, Lin and Phoha, Vir V. and Kong, Fanxin},author+an={2=highlight},booktitle={2023 IEEE Real-Time Systems Symposium (RTSS)},title={Learn-to-Respond: Sequence-Predictive Recovery from Sensor Attacks in Cyber-Physical Systems},year={2023},volume={},number={},pages={78-91},doi={10.1109/RTSS59052.2023.00017}}
RTSS ’23
Catch You if Pay Attention: Temporal Sensor Attack Diagnosis Using Attention Mechanisms for Cyber-Physical Systems
In Cyber-Physical Systems (CPS), sensor data integrity is crucial since acting on malicious sensor data can cause serious consequences, given the tight coupling between cyber components and physical systems. While extensive works focus on sensor attack detection, attack diagnosis that aims to find out when the attack starts has not been well studied yet. This temporal sensor attack diagnosis problem is equally important because many recovery methods rely on the accurate determination of trustworthy historical data. To address this problem, we propose a lightweight data-driven solution to achieve real-time sensor attack diagnosis. Our novel solution consists of five modules, with the attention and diagnosis ones as the core. The attention module not only helps accurately predict future sensor measurements but also computes statistical attention scores for the diagnosis module. Based on our unique observation that the score fluctuates sharply once an attack launches, the diagnosis module determines the onset of an attack through monitoring the fluctuation. Evaluated on high-dimensional high-fidelity simulators and a testbed, our solution demonstrates robust and accurate temporal diagnosis results while incurring millisecond-level computational overhead on Raspberry Pi.
@inproceedings{wang2023catch,series={RTSS '23},keywords={conf},author={Wang, Zifan and Zhang, Lin and Qiu, Qinru and Kong, Fanxin},author+an={2=highlight},booktitle={2023 IEEE Real-Time Systems Symposium (RTSS)},title={Catch You if Pay Attention: Temporal Sensor Attack Diagnosis Using Attention Mechanisms for Cyber-Physical Systems},year={2023},volume={},number={},pages={64-77},doi={10.1109/RTSS59052.2023.00016}}
DAC ’22
Adaptive Window-Based Sensor Attack Detection for Cyber-Physical Systems
Lin Zhang, Zifan Wang, Mengyu Liu, and Fanxin Kong
In Proceedings of the 59th ACM/IEEE Design Automation Conference, 2022
Sensor attacks alter sensor readings and spoof Cyber-Physical Systems (CPS) to perform dangerous actions. Existing detection works tend to minimize the detection delay and false alarms at the same time, while there is a clear trade-off between the two metrics. Instead, we argue that attack detection should dynamically balance the two metrics when a physical system is at different states. Along with this argument, we propose an adaptive sensor attack detection system that consists of three components - an adaptive detector, detection deadline estimator, and data logger. It can adapt the detection delay and thus false alarms at run time to meet a varying detection deadline and improve usability (or false alarms). Finally, we implement our detection system and validate it using multiple CPS simulators and a reduced-scale autonomous vehicle testbed.
@inproceedings{zhang2022adaptive,series={DAC '22},keywords={conf},author={Zhang, Lin and Wang, Zifan and Liu, Mengyu and Kong, Fanxin},author+an={1=highlight},title={Adaptive Window-Based Sensor Attack Detection for Cyber-Physical Systems},year={2022},isbn={9781450391429},publisher={Association for Computing Machinery},address={New York, NY, USA},url={https://doi.org/10.1145/3489517.3530555},doi={10.1145/3489517.3530555},booktitle={Proceedings of the 59th ACM/IEEE Design Automation Conference},pages={919–924},numpages={6},location={San Francisco, California}}
RTSS ’22
Fail-Safe: Securing Cyber-Physical Systems against Hidden Sensor Attacks
@inproceedings{liu2022failsafe,series={RTSS '22},keywords={conf},author={Liu, Mengyu and Zhang, Lin and Lu, Pengyuan and Sridhar, Kaustubh and Kong, Fanxin and Sokolsky, Oleg and Lee, Insup},author+an={2=highlight},booktitle={2022 IEEE Real-Time Systems Symposium (RTSS)},title={Fail-Safe: Securing Cyber-Physical Systems against Hidden Sensor Attacks},year={2022},volume={},number={},pages={240-252},doi={10.1109/RTSS55097.2022.00029}}
DAC ’20
Exploring Inherent Sensor Redundancy for Automotive Anomaly Detection
The increasing autonomy and connectivity have been transitioning automobiles to complex and open architectures that are vulnerable to malicious attacks beyond conventional cyber attacks. Attackers may non-invasively compromise sensors and spoof the controller to perform unsafe actions. This concern emphasizes the need to validate sensor data before acting on them. Unlike existing works, this paper exploits inherent redundancy among heterogeneous sensors for detecting anomalous sensor measurements. The redundancy is that multiple sensors simultaneously respond to the same physical phenomenon in a related fashion. Embedding the redundancy into a deep autoencoder, we propose an anomaly detector that learns a consistent pattern from vehicle sensor data in normal states and utilizes it as the nominal behavior for the detection. The proposed method is independent of the scarcity of anomalous data for training and the intensive calculation of pairwise correlation among senors as in existing works. Using a real-world data set collected from tens of vehicle sensors, we demonstrate the feasibility and efficacy of the proposed method.
@inproceedings{he2020exploring,series={DAC '20},keywords={conf},author={He, Tianjia and Zhang, Lin and Kong, Fanxin and Salekin, Asif},author+an={2=highlight},booktitle={2020 57th ACM/IEEE Design Automation Conference (DAC)},title={Exploring Inherent Sensor Redundancy for Automotive Anomaly Detection},year={2020},month={},volume={},number={},pages={1-6},doi={10.1109/DAC18072.2020.9218557},slides={he2020adaptive_slides.pdf}}
RTSS ’20
Real-Time Attack-Recovery for Cyber-Physical Systems Using Linear Approximations
Attack detection and recovery are fundamental elements for the operation of safe and resilient cyber-physical systems. Most of the literature focuses on attack-detection, while leaving attack-recovery as an open problem. In this paper, we propose novel attack-recovery control for securing cyber-physical systems. Our recovery control consists of new concepts required for a safe response to attacks, which includes the removal of poisoned data, the estimation of the current state, a prediction of the reachable states, and the online design of a new controller to recover the system. The synthesis of such recovery controllers for cyber-physical systems has barely investigated so far. To fill this void, we present a formal method-based approach to online compute a recovery control sequence that steers a system under an ongoing sensor attack from the current state to a target state such that no unsafe state is reachable on the way. The method solves a reach-avoid problem on a Linear Time-Invariant (LTI) model with the consideration of an error bound ε ≥ 0. The obtained recovery control is guaranteed to work on the original system if the behavioral difference between the LTI model and the system’s plant dynamics is not larger than ε. Since a recovery control should be obtained and applied at the runtime of the system, in order to keep its computational time cost as low as possible, our approach firstly builds a linear programming restriction with the accordingly constrained safety and target specifications for the given reach-avoid problem, and then uses a linear programming solver to find a solution. To demonstrate the effectiveness of our method, we provide (a) the comparison to the previous work over 5 system models under 3 sensor attack scenarios: modification, delay, and reply; (b) a scalability analysis based on a scalable model to evaluate the performance of our method on large-scale systems.
@inproceedings{zhang2020realtime,series={RTSS '20},keywords={conf},author={Zhang, Lin and Chen, Xin and Kong, Fanxin and Cardenas, Alvaro A.},author+an={1=highlight},booktitle={2020 IEEE Real-Time Systems Symposium (RTSS)},title={Real-Time Attack-Recovery for Cyber-Physical Systems Using Linear Approximations},year={2020},month={},volume={},number={},pages={205-217},doi={10.1109/RTSS49844.2020.00028},slides={zhang2020realtime_slides.pdf}}
Book Chapters
Book
AI-enabled Real-Time Sensor Attack Detection for Cyber-Physical Systems
Sensor attacks are a severe threat in cyber-physical systems (CPSs) and may cause serious personal casualties and huge economic losses. Adversaries can even non-invasively launch such sensor attacks without much domain knowledge or expensive equipment. The increasingly large scale and high autonomy in CPSs also emphasizes this issue. The strong need motivates many sensor attack detection methods to defend CPSs. AI-enabled sensor attack detection methods stand out among them because they are suitable for dealing with a large amount of CPS data with temporal and spatial dependencies while not requiring domain-specific knowledge. This chapter introduces the background of CPSs and sensor attacks, and demonstrates the workflow of designing AI-enabled sensor attack detectors. Finally, two case studies show how AI empowers sensor attack detection.
@inbook{Zhang2023ai,series={Book},author={Zhang, Lin and Liu, Mengyu and Kong, Fanxin},author+an={1=highlight},keywords={book},editor={Wang, Cliff and Iyengar, S.S. and Sun, Kun},title={AI-enabled Real-Time Sensor Attack Detection for Cyber-Physical Systems},booktitle={AI Embedded Assurance for Cyber Systems},year={2023},publisher={Springer International Publishing},address={Cham},pages={91--120},isbn={978-3-031-42637-7},doi={10.1007/978-3-031-42637-7_6},url={https://doi.org/10.1007/978-3-031-42637-7_6}}
Workshop & Work-in-Process
RTAS ’23
Demo: Simulation and Security Toolbox for Cyber-Physical Systems
The paper describes the design of a simulation and security toolbox for cyber-physical systems, and demonstrates two real-time recovery cases based on the toolbox.
@inproceedings{zhang2023demo,series={RTAS '23},keywords={short},author={Zhang, Lin and Liu, Mengyu and Kong, Fanxin},author+an={1=highlight},booktitle={2023 IEEE 29th Real-Time and Embedded Technology and Applications Symposium (RTAS)},title={Demo: Simulation and Security Toolbox for Cyber-Physical Systems},year={2023},volume={},issn={},pages={357-358},doi={10.1109/RTAS58335.2023.00040},url={https://doi.ieeecomputersociety.org/10.1109/RTAS58335.2023.00040},publisher={IEEE Computer Society},address={Los Alamitos, CA, USA},month=may}
RTAS ’22
Work-in-Progress: Optimal Checkpointing Strategy for Real-time Systems with Both Logical and Timing Correctness
@inproceedings{zhang2022wip,series={RTAS '22},keywords={short},author={Zhang, Lin and Wang, Zifan and Kong, Fanxin},author+an={1=highlight},booktitle={2022 IEEE Real-Time Systems Symposium (RTSS)},title={Work-in-Progress: Optimal Checkpointing Strategy for Real-time Systems with Both Logical and Timing Correctness},year={2022},volume={},number={},pages={515-518},doi={10.1109/RTSS55097.2022.00055}}
Others
Thesis
Real-Time Adaptive Detection and Recovery Against Sensor Attacks in Cyber-Physical Systems
Cyber-physical systems (CPSs) utilize computation to control physical objects in real-world environments, and an increasing number of CPS-based applications have been designed for life-critical purposes. Sensor attacks, which manipulate sensor readings to deceive CPSs into performing dangerous actions, can result in severe consequences. This urgent need has motivated significant research into reactive defense. In this dissertation, we present an adaptive detection method capable of identifying sensor attacks before the system reaches unsafe states. Once the attacks are detected, a recovery approach that we propose can guide the physical plant to a desired safe state before a safety deadline.Existing detection approaches tend to minimize detection delay and false alarms simultaneously, despite a clear trade-off between these two metrics. We argue that attack detection should dynamically balance these metrics according to the physical system’s current state. In line with this argument, we propose an adaptive sensor attack detection system comprising three components: an adaptive detector, a detection deadline estimator, and a data logger. This system can adapt the detection delay and thus false alarms in real-time to meet a varying detection deadline, thereby improving usability. We implement our detection system and validate it using multiple CPS simulators and a reduced-scale autonomous vehicle testbed.After identifying sensor attacks, it is essential to extend the benefits of attack detection. In this dissertation, we investigate how to eliminate the impact of these attacks and propose novel real-time recovery methods for securing CPSs. Initially, we target sensor attack recovery in linear CPSs. By employing formal methods, we are able to reconstruct state estimates and calculate a conservative safety deadline. With these constraints, we formulate the recovery problem as either a linear programming or a quadratic programming problem. By solving this problem, we obtain a recovery control sequence that can smoothly steer a physical system back to a target state set before a safe deadline and maintain the system state within the set once reached. Subsequently, to make recovery practical for complex CPSs, we adapt our recovery method for nonlinear systems and explore the use of uncorrupted sensors to alleviate uncertainty accumulation. Ultimately, we implement our approach and showcase its effectiveness and efficiency through an extensive set of experiments. For linear CPSs, we evaluate the approach using 5 CPS simulators and 3 types of sensor attacks. For nonlinear CPSs, we assess our method on 3 nonlinear benchmarks.
@phdthesis{zhang2023thesis,series={Thesis},author={Zhang, Lin},author+an={1=highlight},year={2023},title={Real-Time Adaptive Detection and Recovery Against Sensor Attacks in Cyber-Physical Systems},journal={ProQuest Dissertations and Theses},booktitle={ProQuest Dissertations and Theses},pages={129},note={Copyright - Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works; Last updated - 2023-06-29},keywords={other},isbn={9798379703868},language={English},url={https://www.proquest.com/dissertations-theses/real-time-adaptive-detection-recovery-against/docview/2827830413/se-2}}