University of Maryland, College Park

NSF Awards · FY 2024 · 2024-03

The transition to 5G is expected to witness not only an emergence of new applications such as mobile augmented and virtual reality, but also opens up the attack surface to both known, and previously unknown threats. Thus, wireless networks of the future will need better control and management at different temporal and traffic aggregation granularities (e.g., how to allocate spectrum, how to quarantine distributed attacks etc.). This project aims to develop scalable, machine learning based analytics on the data from a large set of geographically distributed wireless core network entities such as base stations. The research will enable new approaches for: (a) compressing the raw data via novel summaries and sketches, that reduce overhead while simultaneously enabling highly accurate scalable analytics (b) scalable yet highly flexible distributed learning approaches that are built upon the emerging federated learning paradigm and (c) flexible allocation of bandwidth to support the control plane analytics that minimizes the impact on the data plane. The proposed research outcomes will be systems, algorithms, and data analytics workflows that will inform the design and management of next generation critical wireless infrastructures. The approaches developed will enable ISPs to better apportion resources and enable better performance for emerging augmented reality applications for societal benefit (e.g., disaster response and management). In addition, the approaches can enable the discovery and profiling of new threats, which will have significant implications on national security. The proposed education activities are expected to provide students with a comprehensive training in networking, security, system building, and data science. Thus, there is significant potential for broader impact in terms of contributions to workforce development in an area of national need. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Awards · FY 2023 · 2023-10

With the growth of the Internet and its importance in supporting the US economy, business, health, education and other services, it is critical to ensure both high performance and high availability of the networks underlying it. Increasingly, such networks include a heterogeneous set of network switches and other devices which must be monitored and controlled in a coordinated manner. Emerging networked applications, such as cloud gaming or cloud streamed augmented reality, are expected to further stress both control systems and network monitoring by requiring real-time response to rapid changes in traffic workloads. This project aims to address the needs of future network control by enabling a network telemetry infrastructure that can provide timely, accurate, and trusted information about ongoing activities in the network This project proposes FROOT, a future-proof, trustworthy telemetry infrastructure for networks of heterogeneous programmable devices (e.g., programmable switch, SmartNIC, CPU, and DPU). The project takes an interdisciplinary approach spanning algorithms, systems, and security to inform the design and implementation of next generation telemetry systems through the following: (1) universal sketch-based algorithmic design and implementation for current and new measurement tasks and network devices; (2) novel network-wide resource optimization for handling network dynamics; and (3) trustworthy sketch deployment into heterogeneous devices to obtain critical telemetry information. The researchers also plan to deploy their network telemetry system at Mass Open Cloud testbed, an open public cloud project led by Boston University and other institutions in Massachusetts. The project will result in the development of open-source tools, algorithms, and prototype implementations that will reduce the time to deploy sketch-based telemetry in real-world scenarios. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Awards · FY 2023 · 2023-10

Cyber-attacks are becoming increasingly advanced and sophisticated. Advanced attackers monitor their targets for a long time to find out about their vulnerabilities and protective strategies. Such advanced attacks are extremely challenging to prevent and investigate due to their sophisticated and advanced tactics and resources and by their strategy to penetrate the system in unexpected/overlooked ways. Worse, attackers use sophisticated tactics, such as obfuscation and evasive techniques, to thwart or delay forensics investigations. Attackers also compromise a wide range of system components and resources, making it extremely difficult to restore and harden the system. Delayed or incomplete forensic analysis makes it difficult to properly secure the victim’s organization on time, leading to significant damages and losses. To this end, this project develops novel techniques to (1) prevent diverse attacks thoroughly, (2) conduct rapid and comprehensive forensic analysis, and (3) protect the victim’s system rigorously. This project also involves educational activities that broadens participation in computing, by organizing mentoring workshops and coaching the University of Virginia’s Collegiate Cyber Defense Competition team, which includes many female students. This project aims to develop an automated forensic-in-the-loop cyber defense infrastructure that coherently integrates novel defenses, forensic analysis, and hardening approaches. First, the investigator develops attack vector agnostic protection and detection approaches by perturbing inputs and runtime environments that are the weakest links of the attacks. Second, the investigator develops novel automated techniques to detect and eliminate anti-forensic techniques applied to malware. Furthermore, to handle evasive malware, the investigator introduces the adaptive counterfactual execution technique to evolve the runtime environment and execution context. Finally, the investigator develops an automated root cause analysis technique that diagnoses loopholes and identifies potential fixes (e.g., secure configurations). This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Awards · FY 2023 · 2023-10

Recently, there have been increasing efforts to advance emerging technologies, which bring significant advantages for machine learning (ML) in terms of power efficiency, computational efficiency, and sustainability. With the considerable benefits in energy efficiency, there are significant interests in leveraging optical computing into applications, such as medical sensing, security screening, drug detection, and autonomous driving. Specifically, optical computing offers unique advantages in power efficiency and extreme computation speed, leading to significant performance improvements compared to digital computing systems for ML tasks. This project aims to develop an end-to-end design infrastructure to advance optical computing for ML, covering from low-level physics to algorithms to full-stack system design. This will generate broader impacts in cross-disciplinary research and real-world application fields from physics to computer science to ML. This project will produce an open-source design infrastructure, LightRidge, and conference tutorials to facilitate technology transfers and fruitful industry-academia interactions in a multidisciplinary community. This project aims to develop an open-source, end-to-end design infrastructure, LightRidge, to explore and advance Diffractive Deep Neural Networks (DONNs) in real-world ML tasks. DONNs utilize the free-space light diffraction to form an optical feed-forward network like conventional DNNs architecture, which can host millions of neurons in each layer that are interconnected with those in neighboring layers, offering orders of magnitude energy efficiency improvements over general-purpose processor and domain-specific accelerators. However, there are several critical technical barriers in the design, training, exploration, and hardware deployment of DONNs. Thus, this project will produce an agile end-to-end design and fabrication programming framework LightRidge, consisting of precise, versatile, and differentiable optical physics kernels powered by domain-specific high-performance-computing developments, with novel physics-aware hardware-software codesign methodologies to strengthen the correlations between algorithm modeling and physical hardware. This project will also develop an intelligent and efficient design space exploration (DSE) engine LightRidge-DSE, to enable architectural and fabrication parameters exploration, monolithic on-chip DONNs integration, and demonstrate real-world all-optical ML tasks. Finally, LightRidge will be fully released as an open-source hardware project, which will contribute to multidisciplinary research domains such as physics, electrical engineering, computer science, and can be used as a new education platform. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.