Marco Gruteser
Marco Gruteser is a Principal Research Scientist at Google leading teams focused on the privacy and security of AI agents and edge AI. Prior to joining Google, he was the Peter D. Cherasia Faculty Scholar and Professor at Rutgers University and served as chair of ACM SIGMOBILE. Over the years, he has worked in location privacy, mobile systems, and connected vehicles, receiving multiple award paper recognitions. A list of publications is available on Google Scholar.
Research Areas
Authored Publications
Sort By
Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle
Sahar Abdelnabi
Borja de Balle Pigem
Sebastian Benthall
Eleanor Birrell
Kamalika Chaudhuri
Madiha Zahrah Choksi
Rachel Cummings
Adam Davies
Dj Dvijotham
Seliem El-Sayed
Ferdinando Fioretto
Matt Franchi
Adria Gascon
Roxana Geambasu
Sahra Ghalebikesabi
Hamed Haddadi
Jamie Hayes
Ashish Hooda
Amir Houmansadr
Somesh Jha
Chloé Kiddon
Tadayoshi Kohno
Abdullatif Köksal
Haoran Li
Tianshi Li
Nathan Malkin
Sarah Meiklejohn
Niloofar Mireshghallah
Sewoong Oh
Katherine Ortiz
Francesco Pinto
Franziska Roesner
Edo Roth
Jacqueline Rowe
Khawaja Shams
Ilia Shumailov
Yan Shvartzshnaider
Dawn Song
Jose Such
Octavian Suciu
Pierre Tholoniat
Trishita Tiwari
Hal Triedman
Ren Yi
Wen Zhang
Xuhui Zhou
Kassem Fawaz
Stefan Mellem
Helen Nissenbaum
Google (2026)
Preview abstract
The vision of an ecosystem of general and highly capable autonomous agents challenges accepted principles of secure and privacy-preserving system engineering. Inspired by the theory of Contextual Integrity, we argue that in order for agents to act appropriately, their behaviors should comply with societal norms and expectations. This manuscript explores contextual approaches to engineering agentic systems that embody an understanding of societal norms and uphold the appropriateness of actions by design. It presents a list of key open research problems in this area to create awareness among the broader research community across academia, government, and industry.
View details
Confidential Federated Computations
Hubert Eichner
Kallista (Kaylee) Bonawitz
Dzmitry Huba
Brett McLarnon
Timon Van Overveldt
Nova Fallen
Albert Cheu
Katharine Daly
Adria Gascon
ArXiv (2024)
Preview abstract
Federated Learning and Analytics (FLA) have seen widespread adoption by technology platforms for processing sensitive on-device data. However, basic FLA systems have privacy limitations: they do not necessarily require anonymization mechanisms like differential privacy (DP), and provide limited protections against a potentially malicious service provider. Adding DP to a basic FLA system currently requires either adding excessive noise to each device's updates, or assuming an honest service provider that correctly implements the mechanism and only uses the privatized outputs. Secure multiparty computation (SMPC) -based oblivious aggregations can limit the service provider's access to individual user updates and improve DP tradeoffs, but the tradeoffs are still suboptimal, and they suffer from scalability challenges and susceptibility to Sybil attacks. This paper introduces a novel system architecture that leverages trusted execution environments (TEEs) and open-sourcing to both ensure confidentiality of server-side computations and provide externally verifiable privacy properties, bolstering the robustness and trustworthiness of private federated computations.
View details
Mayfly: Private Aggregate Insights from Ephemeral Streams of On-Device User Data
Ren Yi
Ollie Guinan
Albert Cheu
Christopher Bian
Yannis Guzman
Edo Roth
Zoe Gong
Maya Spivak
Artem Lagzdin
Stanislav Chiknavaryan
Ryan McKenna
Grace Ni
Timon Van Overveldt
2024
Preview abstract
This paper introduces Mayfly, a federated analytics approach enabling aggregate queries over ephemeral on-device data streams without central persistence of sensitive user data. Mayfly minimizes data via on-device windowing and contribution bounding through SQL-programmability, anonymizes user data via streaming differential privacy (DP), and mandates immediate in-memory cross-device aggregation on the server -- ensuring only privatized aggregates are revealed to data analysts. Deployed for a sustainability use case estimating transportation carbon emissions from private location data, Mayfly computed over 4 million statistics across more than 500 million devices with a per-device, per-week DP ε=2 while meeting strict data utility requirements. To achieve this, we designed a new DP mechanism for Group-By-Sum workloads leveraging statistical properties of location data, with potential applicability to other domains.
View details
EdgeSharing: Edge Assisted Real-time Localization and Object Sharing in Urban Streets
Luyang Liu
The 40th IEEE International Conference on Computer Communications (IEEE INFOCOM 2021). (2021)
Preview abstract
Collaborative object localization and sharing at smart intersections promises to improve situational awareness of traffic participants in key areas where hazards exist due to visual obstructions. By sharing a moving object's location between different camera-equipped devices, it effectively extends the vision of traffic participants beyond their field of view. However, accurately sharing objects between moving clients is extremely challenging due to the high accuracy requirements for localizing both the client position and positions of its detected objects. Existing approaches based on direct sharing between devices are limited by the computational resources of (potentially legacy) vehicles and bad flexibility. To address these challenges, we introduce EdgeSharing, a novel localization and object sharing system leveraging the resources of edge cloud platforms. EdgeSharing holds a real-time 3D feature map of its coverage region on the edge cloud and uses it to provide accurate localization and object sharing service to the client devices passing through this region. We further propose several optimization techniques to increase the localization accuracy, reduce the bandwidth consumption and decrease the offloading latency of the system. The result shows that the system is able to achieve a mean vehicle localization error of 0.2813-1.2717 meters, an object sharing accuracy of 82.3\%-91.44\%, and a 54.68\% object awareness increment in urban streets and intersections. In addition, the proposed optimization techniques are able to reduce 70.12\% of bandwidth consumption and reduce 40.09\% of the end-to-end latency.
View details
Elf: Accelerate High-resolution Mobile Deep Vision with Content-aware Parallel Offloading
Wuyang Zhang
Zhezhi He
Luyang Liu
Zhenhua Jia
Yunxin Liu
Dipankar Raychaudhuri
Yanyong Zhang
The 27th Annual International Conference on Mobile Computing and Networking (ACM MobiCom 2021). (2021)
Preview abstract
A broad class of computer vision algorithms on images or videos collected by mobile devices greatly benefit from deep learning for high application performance. Meanwhile, these applications often demand real-time responses (e.g., <100ms), which can hardly be satisfied with mobile devices of limited computation capability. Offloading the computation from mobile devices to edge clouds has been recently proposed as a promising approach. However, the previous work assumes that there always exist dedicated and powerful edge servers that put all the computing resources for a single offloading job. This assumption can hardly be true consistently due to the distributed nature of edge cloud and dynamic resource needs from mobile users.
In this work, we propose and design a system called \textit{Elf} to accelerate the deep neural network inference for vision application running on mobile devices. Elf is customized to minimize the end-to-end latency, through the intelligent content partition and multi-edge server offloading. In particular, instead of offloading an entire high-resolution video-clips to a single edge server naively, we perform intelligent partitions on the high-resolution video-clips in a content-/resource-aware fashion. Such partition leverages various techniques, including Region-Proposal (RP) complexity estimation, RP location prediction and Low-Resolution Compensation (LRC), which dynamically assigns the partitions to different computation servers. Comprehensive experiments are performed to demonstrate that the Elf system can effectively reduce the end-to-end latency of multi-object segmentation tasks on DAVIS2017 by 88.5\%, 94.6\% and 33.8\%, in comparison to NVIDIA Jetson TX2, Nano and single object counterparts.
View details
LiveTraVeL: Real-time matching of transit vehicle trajectories to transit routes at scale
Georg Osang
James Cook
Proceedings of IEEE Intelligent Transportation Systems Conference 2019 (2019)
Preview abstract
We present LiveTraVeL (Live Transit Vehicle Labeling), a real-time system to label a stream of noisy observations of transit vehicle trajectories with the transit routes they are serving (e.g., northbound bus #5). In order to scale efficiently to large transit networks, our system first retrieves a small set of candidate routes from a geometrically indexed data structure, then applies a fine-grained scoring step to choose the best match. Given that real-time data remains unavailable for the majority of the world’s transit agencies, these inferences can help feed a real-time map of a transit system’s trips, infer transit trip delays in real time, or measure and correct noisy transit tracking data. This system can run on vehicle observations from a variety of sources that don’t attach route information to vehicle observations, such as public imagery streams or user-contributed transit vehicle sightings.
We abstract away the specifics of the sensing system and demonstrate the effectiveness of our system on a “semisynthetic” dataset of all New York City buses, where we simulate sensed trajectories by starting with fully labeled vehicle trajectories reported via the GTFS-Realtime protocol, removing the transit route IDs, and perturbing locations with synthetic noise. Using just the geometric shapes of the trajectories, we demonstrate that our system converges on the correct route ID within a few minutes, even after a vehicle switches from serving one trip to the next.
View details
Advances and Open Problems in Federated Learning
Brendan Avent
Aurélien Bellet
Mehdi Bennis
Arjun Nitin Bhagoji
K. A. Bonawitz
Graham Cormode
Rachel Cummings
Rafael G.L. D'Oliveira
Salim El Rouayheb
David Evans
Josh Gardner
Adrià Gascón
Phillip B. Gibbons
Zaid Harchaoui
Chaoyang He
Lie He
Zhouyuan Huo
Justin Hsu
Martin Jaggi
Tara Javidi
Gauri Joshi
Mikhail Khodak
Jakub Konečný
Aleksandra Korolova
Farinaz Koushanfar
Sanmi Koyejo
Tancrède Lepoint
Yang Liu
Prateek Mittal
Richard Nock
Ayfer Özgür
Rasmus Pagh
Ramesh Raskar
Dawn Song
Weikang Song
Sebastian U. Stich
Ziteng Sun
Florian Tramèr
Praneeth Vepakomma
Jianyu Wang
Li Xiong
Zheng Xu
Qiang Yang
Felix X. Yu
Han Yu
Arxiv (2019)
Preview abstract
Federated learning (FL) is a machine learning setting where many clients (e.g., mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g., service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and mitigates many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this paper discusses recent advances and presents a comprehensive list of open problems and challenges.
View details
Federated Learning with Autotuned Communication-Efficient Secure Aggregation
K. A. Bonawitz
Fariborz Salehi
Jakub Konečný
Asilomar Conference on Signals, Systems, and Computers (2019)
Preview abstract
Federated Learning enables mobile devices to collaboratively learn a shared inference model while keeping all the training data on device, decoupling the ability to do machine learning from the need to store the data in the cloud. Existing work on federated learning with limited communication demonstrates how random rotation can enable users' model updates to be quantized much more efficiently, reducing the communication cost between users and the server. Meanwhile, secure aggregation enable the server to learn an aggregate of at least a threshold number of device's model contributions without observing any individual device's contribution in unaggregated form. In this paper, we highlight some of the challenges of setting the parameters for secure aggregation to achieve communication efficiency, especially in the the context of the aggressively quantized inputs enabled by random rotation. We then develop a recipe for auto-tuning communication-efficient secure aggregation, based on specific properties of random rotation and secure aggregation -- namely, the predictable distribution of vector entries post-rotation and the modular wrapping inherent in secure aggregation. We present both theoretical results and initial experiments.
View details
