New vulnerabilities arise in Cyber-Physical Systems (CPS) as new technologies are integrated to interact and control physical systems. In addition to software and network attacks, sensor attacks are a crucial security risk in CPS, where an attacker alters sensing information to negatively interfere with the physical system. Acting on malicious sensor information can cause serious consequences. While many research efforts have been devoted to protecting CPS from sensor attacks, several critical problems remain unresolved. First, existing attack detection works tend to minimize the detection delay and false alarms at the same time; this goal, however, is not always achievable due to the inherent trade-off between the two metrics. Second, there has been much work on attack detection, yet a key question remains concerning what to do after detecting an attack. Importantly, a CPS should detect an attack and recover from the attack before irreparable consequences occur. Third, the interrelation between detection and recovery has met with insufficient attention: Integrating detection and recovery techniques would result in more effective defenses against sensor attacks.

This project aims to address these key problems and develop novel detection and recovery techniques. The project aims to achieve timely and safe defense against sensor attacks by addressing real-time adaptive-attack detection and recovery in CPS. First, this project explores new attack detection techniques that can dynamically balance the trade-off between the detection delay and the false-alarm rate in a data-driven fashion. In this way, the detector will deliver attack detection with predictable delay and maintain the usability of the detection approach. Second, this project pursues new recovery techniques that bring the system back to a safe state before a recovery deadline while minimizing the degradation to the mission being executed by the system. Third, this project investigates efficient techniques that address the attack detection and recovery in a coordinated fashion to significantly improve response to attacks. Specific research tasks include the development of real-time adaptive sensor attack detection techniques, real-time attack recovery techniques, and attack detection and recovery coordination techniques. The developed techniques will be implemented and evaluated on multiple CPS simulators and an autonomous vehicle testbed.

Human interaction with autonomous cyber-physical systems is becoming ubiquitous in consumer products, transportation systems, manufacturing, and many other domains. This project seeks constructive methods to answer the question: How can we design cyber-physical systems to be responsive and personalized, yet also provide high-confidence assurances of reliability? Cyber-physical systems that adapt to the human, and account for the human's ongoing adaptation to the system, could have enormous impact in everyday life as well as in specialized domains (biomedical devices and systems, transportation systems, manufacturing, military applications), by significantly reducing training time, increasing the breadth of the human's experiences with the system prior to operation in a safety-critical environment, improving safety, and improving both human and system performance. Architectures that support dynamic interactions, enabled by advances in computation, communication, and control, can leverage strengths of the human and the automation to achieve new levels of performance and safety.

This research investigates a human-centric architecture for "cognitive autonomy" that couples human psychophysiological and behavioral measures with objective measures of performance. The architecture has four elements: 1) a computable cognitive model which is amenable to control, yet highly customizable, responsive to the human, and context dependent; 2) a predictive monitor, which provides a priori probabilistic verification as well as real-time short-term predictions to anticipate problematic behaviors and trigger the appropriate action; 3) cognitive control, which collaboratively assures both desired safety properties and human performance metrics; and 4) transparent communication, which helps maintain trust and situational awareness through explanatory reasoning. The education and outreach plan focuses on broadening participation of underrepresented minorities through a culturally responsive undergraduate summer research program, which will also provide insights about learning environments that support participation and retention. All research and educational material generated by the project are being made available to the public through the project webpage.

Complex cyber-physical systems (CPS) that operate in dynamic and uncertain environments will inevitably encounter unanticipated situations during their operation. Examples range from naturally occurring faults in both the cyber and physical components to attacks launched by malicious entities with the purpose of disrupting normal operations. As infrastructures, e.g. energy, transportation, industrial systems and built environments, are getting smarter, the chance of a fault or attack increases. When this happens, it is essential that system behavior remains viable, i.e., it does not violate pre-specified operating constraints on run-time behavior. Preserving safety, for instance, is of paramount importance to avoid damage and possible loss of life. This project will develop strategies for mitigating the effects of such unanticipated situations, that seek to optimize for performance (measured by multiple metrics such as cost, efficiency, accuracy, etc.) without compromising viability. The emphasis will be on the automotive application domain, given the upcoming revolution brought by innovations such as vehicle-to-vehicle (V2V), vehicle to infrastructure (V2I) communication and autonomous driving, and because of the safety-criticality of the transportation infrastructure. To ground our research on relevant problems, we will engage industrial partners. The outcomes of the project will be validated upon test scenarios drawn from the automotive industry. 

Fundamental issues arising when safety-critical CPS operate in uncertain environments will be addressed, with the objective of obtaining a better understanding of, and developing optimal or near-optimal strategies for dealing with, emergent problems that arise from the interaction of resource-allocation and control strategies in such systems. One of the novelties of the technical approach adopted in this project is to closely integrate three different CPS perspectives control theory, automotive & aerospace application domain-knowledge, and real-time resource management & scheduling in order to develop run-time mitigation strategies for complex CPS's operating in dynamic and uncertain environments, and exposed to a variety of faults. Such an integrated approach will allow for the identification of emergent problems that arise from the interaction of resource-allocation and control algorithms, that may otherwise remain undiscovered if the control and resource-allocation aspects were considered separately.
The general design-time and run-time tools for creating resilient CPSs will be guided by the implementation and evaluation of the research in simulation and on laboratory test-beds upon three applications from the automotive domain: fault resilience for variable-valve internal combustion engines; fail-safe energy management for hybrid-electric vehicles; and robust sensor management for autonomous vehicles.
 

Deep Neural Networks (DNN) enabled Cyber-Physical Systems (CPS) hold great promise for revolutionizing many industries, such as drones and self-driving cars. However, the current generation of DNN cannot provide analyzable behaviors and verifiable properties that are necessary for safety assurance. This critical flaw in purely data-driven DNN sometimes leads to catastrophic consequences, such as vehicle crashes linked to self-driving and driver-assistance technologies. On the other hand, physics-model-based engineering methods provide analyzable behaviors and verifiable properties, but do not match the performance of DNN systems. These considerations motivate the work in this project which aims at physics-model-based neural networks (NN) redesign, yielding HyPhy-DNN: a hybrid self-correcting physics-enhanced DNN framework. HyPhy-DNN will provide the performance of DNNs and the analyzability and verifiability of physical models, thus providing a foundation for verifiably safe self-driving cars, drones, and other CPS systems. Moreover, the HyPhy-DNN will fundamentally advance the integration of deep learning and robust control to enable safety- and time-critical CPS to safely operate with high performance in unforeseen and dynamic environments.

The HyPhy-DNN will make three innovations in redesigning NN architecture: (i) Physics augmentations of NN inputs for directly capturing hard-to-learn physical quantities and embedding Taylor series; (ii) Physics-guided neural network editing, such as removing links between independent physics variables or fixed weights on links between certain physics variables to maintain the known physics identity such as in conservation laws; and (iii) Time-frequency-representation filtering-based activations for filtering out noise having dynamic frequency distribution. The novel architectural redesigns will empower the HyPhy-DNN with four targeted capabilities: 1) controllable and provable model accuracy; 2) maximum avoidance of spurious correlations; 3) strict compliance with physics knowledge; and 4) automatic correction of unsafe control commands. Finally, the safety certification of any DNN will be a long-term challenge. Hence, the HyPhy-DNN shall have a simple but verified backup controller for guaranteeing safe and stable operation in dynamic and unforeseen environments. To achieve this, the research team will integrate HyPhy-DNN with an adaptive-model-adaptive-control (AMAC) framework, the core novelty of which lies in fast and accurate nonlinear model learning via sparse regression for model-based robust control. The HyPhy-DNN and AMAC are complementary and will be interactive at different scales of system performance and functionalities during the safety-status-cycle, supported by the Simplex software architecture, a well-known real-time software technology that tolerates faults and allows online control system upgrades.

Many emerging cyber-physical systems (CPS) are composed of a network of autonomous agents that make high-impact decisions, for example, a network of robots or drones that are on a search and rescue (SAR) mission. Such systems are referred to as high-impact decision making cyber-physical systems (HI-CPS). This research aims at building a unified theoretical framework for HI-CPS and validating this framework by fully implementing and testing a concrete example of such systems, namely, a network of autonomous agents that search for a lost person in dire conditions. This research brings together concepts from probability theory, decision theory, information theory, wireless networks, machine learning, and transportation engineering. By definition, this research focuses on high-impact systems, and it can directly impact the design of important emerging real-life systems. Educational and outreach activities are well-integrated into the research and include developing an honors thesis seminar course, workshops for underrepresented groups, and creating open educational content. 

The research has two thrusts: In Thrust 1, a new general theory of decision making suitable for such high-impact decision making is developed. This is based on the novel idea that the very notion of probability is insufficient when we are making high-impact decisions. It is shown that the approach is a multi-dimensional generalization of expected utility. A universality result is proved showing that any other decision-making operation can be framed as a special case of the proposed approach, emphasizing the sufficiency of the approach. Thrust 2 focuses on extending the framework to include two vital factors in HI-CPS: (1) timeliness and efficiency of information transmission as well as (2) power management. Thus, HI-CPS is designed and developed by incorporating all of these factors into a decision-making framework. To validate the theory, a concrete example of HI-CPS, i.e., an SAR system using a network of autonomous agents is built and tested. This research directly addresses Science of Cyber-Physical Systems (CPS) by providing new models and theories that unify HI-CPS.

Many emerging cyber physical systems are composed of a large number of mobile intelligent agents. In these systems, each agent travels along a trajectory that is often not pre-determined. At any time interval, new agents might appear in the system, and some existing agents might disappear. Additionally, these agents are normally capable of communicating with each other or outside stations using wireless communications. We refer to these systems as Trajectory-Based Cyber-Physical Networks (TCN). Examples of such systems are abundant and range from future generations of Unmanned Aircraft Systems (UAS) to networks of human or robot agents that are deployed in an area to perform missions such as disaster recovery. The goal of this research is (1) to develop a unifying theory called "Trajectory Process Theory" for TCNs, and (2) to design, implement, and test two specific real-life TCNs based on the proposed theory.

This research has two main thrusts: Thrust 1 builds the foundations of Trajectory Process Theory. Thrust 2 applies the theory to UAS technologies, specifically aerial base stations and unmanned aircraft delivery systems. This research brings together concepts from probability theory, stochastic geometry, wireless networks, and transportation engineering. The proposed research can directly impact the design of important emerging real life systems such as UASs. Educational and outreach activities including workshops for underrepresented groups as well as creating open educational content are undertaken.

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).

Medical Cyber-Physical Systems (MCPS) increasingly rely on complex and connected software and artificial intelligence for control and decision making in various diagnostic and therapeutic applications. But contrary to other CPS, they often depend on advanced medical knowledge and human expertise for real-time operation. Tele-operated surgical robots for minimally invasive surgery are an example of the most complex human-in-the-loop MCPS, envisioned to enable remote operations in inaccessible areas, low-resource populations, and extreme environments. However, an increasing number of recalls and adverse event reports have shown the vulnerability of MCPS to accidental or maliciously-crafted faults and human errors with potential negative impacts on patients. The objective of this research is to investigate the fundamental problem of runtime safety assurance in human-in-the-loop MCPS, and to develop integrated model and data-driven capabilities for timely detection and mitigation of safety hazards and reducing the risk of harm to patients.

The proposed research will advance the state-of-the-art in runtime verification and anomaly detection by introducing three novel principles for design of context-aware safety engines for MCPS: (i) Formal specification and learning of human-cyber-physical system contexts and their relationship with potentially unsafe control actions that lead to hazards and accidents; (ii) Real-time inference of the human-cyber-physical context through multi-level monitoring and model-based state estimation to detect the likelihood, timing, and risk of impending hazards; (iii) Risk-aware hazard mitigation through the context-aware generation of safe and corrective response actions that prevent adverse consequences in the physical layer. The research activities will be integrated with education through multi-disciplinary curriculum development and hands-on training for graduate students, research experience for undergraduates, and engagement activities, including summer internships, Girls? Geek Days, tech camps, and hackathons for K-12 students. These activities aim to broaden the participation of students from underrepresented groups and minorities in CPS and engineering in medicine research and train the next generation of diverse CPS professionals with expertise in areas such as healthcare, robotics, safety, and security that have the potential for significant societal impact.

Smart manufacturing, in which manufacturing processes become increasingly automated using algorithms intended to boost profits and reduce resource use while decreasing human error, is expected to enhance production efficiency in industries where chemical reaction, separation, and transport are important. Heightened communication and automation are also impacting other industries that involve control of molecular-level processes, as in healthcare, water treatment, and irrigation. However, a challenge for enhanced automation of these processes is preventing cyberattacks on the systems (referred to as control systems) that perform communication and computation to enable automation. If a cyberattack on a control system succeeds, it may impact factors such as safety, profitability, or production volume. Though safety-critical industries have many defenses in place to seek to prevent attackers from causing harm, an open question is how to design stronger safeguards against successful attacks into automation systems. This work aims to develop fundamental advances in advanced control algorithms integrated with algorithms for detecting cyberattacks and alerting company personnel to their presence for chemical processes described by complex dynamic models. This project seeks to characterize the conditions under which the process automation algorithms can be made resilient to cyberattacks on various aspects of the automation systems (e.g., sensors and actuators) in the sense that attacks cannot succeed at creating problematic process behavior from a safety standpoint even if they breach certain information technology defenses. The project will also pursue the development of a number of algorithms for enhancing safety and efficiency for next-generation manufacturing, and explore how cyberattacks may impact these. To disseminate information on these topics broadly, a live action and an animated short video to be shared via YouTube will be developed, in which the plot and the world in which the characters live expose viewers to the concepts of control, cybersecurity, and engineering pursued in this research through story.

The planned research program will comprehensively evaluate the characteristics of cyberattacks for processes involving molecular-level phenomena of different types, and will develop fundamental advances in control theory and algorithms for enhancing cybersecurity for these processes through control designs integrated with other frameworks such as detection algorithms. The theoretical conditions under which cybersecurity is enhanced by the proposed developments (in the sense that the attacks cannot create a safety issue for the process) will be characterized. Specifically, the following will be addressed: a) a mathematical formalization of the definition of different types of "undesirable behavior" for various chemical processes and clarification of reasonable types of cyberattacks for different chemical process systems will be developed; b) control and state estimation designs will be combined with detection techniques to allow guarantees to be developed on the conditions under which a cyberattack cannot create undesirable behavior even if it penetrates certain information technology defenses; c) novel sensing and control capabilities for cyber-physical systems will be developed that take advantage of machine learning and mathematics to increase flexibility of chemical processes, with investigations of how these advances may be cyberattacked; d) techniques for understanding and preventing undesirable behavior during a cyberattack through physical means (e.g., materials/equipment design and selection) will be developed; and e) the developments will be demonstrated and evaluated within the context of chemical processes across a variety of industries. These developments will focus on processes described by nonlinear dynamic models under model predictive control, but will also make extensions to processes of other types (e.g., a class of stochastic differential equations or partial differential equations).

Connected vehicles are an integral part of the future of intelligent transportation systems. They use wireless and sensing technologies to enable communication and cooperation between vehicles and infrastructure. Nonetheless, sensor reliability and data integrity play a crucial role in these vehicles. As vehicles and infrastructures grow increasingly networked and automated, there is a pressing need to identify sensor-related anomalies and mitigate potential safety hazards they might pose. The overarching goal of this project is to protect the connected vehicular network against anomalous sensor readings from any cause to ensure the safety of vehicles and passengers. The research aims to (1) provide new capabilities to broadly address safety concerns in connected vehicles to meet emerging future needs of intelligent transportation systems, and (2) enable a diverse and inclusive community of scientists and engineers to work in multidisciplinary areas such as cognitive machine learning and cybersecurity.

With the ever increasing complexity of connected vehicles operating in a more complicated cyber-physical social environment, conventional anomaly detection methods will likely not be able to keep pace with the demands of these challenges and function safely in a tomorrow's smart and connected communities. This project will explore (1) novel algorithmic methods that will enable the vehicles to quickly classify different types of sensor failures, learn new emerging anomalous patterns of sensor activity, and assess their risks relative to vehicle safety, and (2) designs for efficient scalable safe multi-agent models to build reputational trust among the connected vehicles in order to facilitate V2V information sharing, learning, and cooperative decision-making, and (3) new consensus-based protocols for connected vehicles that provide for resilience and adaptivity in the presence of disruptions, interruptions, and changes to vehicle participation. Initial test and evaluations are conducted by computer simulations with publicly-available data sets on connected vehicles and autonomous systems.

Advances in artificial intelligence (AI) make it clear that intelligent systems will account for the next leap in scientific progress to enable a myriad of future applications that improve the quality of life, contribute to the economy, and enhance societal resilience to a broad spectrum of disruptions. Yet, advances in AI come at a considerable resource costs. To reduce the cost of AI, this project takes inspiration from biological systems. It is well-known that a key bottleneck in AI is the perception subsystem. It is the part that allows AI to perceive and understand its surroundings. Humans are very good at understanding what?s critical in their environment and the human perceptual system automatically focuses limited cognitive resources on those elements of the scene that matter most, saving a significant amount of ?brain processing power?. Current AI pipelines do not have a similar mechanism, resulting in significantly higher resource costs. The project refactors data analytics and machine intelligence pipelines to allow for better prioritization of external stimuli leveraging and significantly extending advances in scheduling previously developed in the real-time systems research community. The refactored AI pipeline will improve the efficiency and efficacy of AI-enabled systems, allowing them to be safer and more responsive, while at the same time significantly lowering their cost. If successful, the project will help bring machine intelligence solutions to the benefit of all society. This is achieved through interactions between research, education, and outreach, as well as integration of multiple scientific communities, including (i) researchers on embedded computing who offer platforms and schedulers, (ii) researchers on IoT and networking, and (iii) researchers on intelligent applications and application domain experts. The work is an example of cyber-physical computing research, where a new generation of digital algorithms learn to exploit a better understanding of physical systems in order to improve societal outcomes. 

The project removes systemic priority inversion from machine intelligence pipelines in modern neural-network-based cyber-physical applications. In general, priority inversion occurs in real-time systems when computations that are less critical (or with longer deadlines) are performed ahead of those that are more critical (or with shorter deadlines). The current state of machine intelligence software suffers from significant priority inversion on the path from perception to decision-making, resulting in vastly inferior system responsiveness to critical events, thereby jeopardizing safety and increasing the cost of hardware to meet application needs. By resolving this problem, this project shall improve system ability to react to critical inputs, while at the same time significantly reducing platform cost. The intellectual merit of the project lies in investigating the intersection of two core areas in cyber-physical computing: (i) data analytics and machine learning and (ii) real-time systems. Specifically, the project refactors data analytics and machine intelligence pipelines to remove priority inversion. Mitigation of priority inversion problems in different systems has been one of the key contributions of the real-time community. Removal of priority inversion from machine intelligence pipelines makes several other scientific contributions. Namely, (i) the refactored AI pipeline improves the efficiency and efficacy of AI-enabled mission-critical systems, (ii) it enables autonomous systems to be more responsive, while lowering their cost, and (iii) it contributes to safety of intelligent systems by ensuring that critical inputs are processed first. The project expects to demonstrate significant improvements in performance of modern machine-learning-based inference protocols, while offering service differentiation that dramatically improves predictability and timeliness of reactions to critical situations. If successful, the project will significantly reduce the cost of deploying machine intelligence solutions in future cyber-physical systems, while improving predictability and temporal guarantees. In addition to delivering the technical contributions of this project, an explicit purpose of the work is to advance education and workforce development on Intelligent CPS topics. This is achieved through interactions between activities for research, education, and broadening participation, as well as integration of multiple communities, including (i) researchers on embedded computing who offer platforms and schedulers, (ii) researchers on IoT and networking, and (iii) researchers on intelligent applications and application domain experts.