Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 10406 publications
Mix&Slice
Marco Rosa
Encyclopedia of Cryptography, Security and Privacy, Springer Nature Switzerland (2025), pp. 1550-1555
Preview abstract
Mix&Slice is an encryption technique that enables efficient and robust access revocation on resources stored at external cloud providers. The technique makes use of a transformation that provides strong inter-dependency in the encrypted representation of a resource. To perform access revocation, it is then sufficient to re-encrypt a small portion of the resource to have guarantees that the resource (and any of its parts) will become unintelligible to those from whom access has been revoked.
View details
Scalable Private Partition Selection via Adaptive Weighting
Justin Y. Chen
Forty-second International Conference on Machine Learning (2025)
Preview abstract
In the differentially private partition selection problem (a.k.a. private set union, private key discovery), users hold subsets of items from an unbounded universe. The goal is to output as many items as possible from the union of the users' sets while maintaining user-level differential privacy. Solutions to this problem are a core building block for many privacy-preserving ML applications including vocabulary extraction in a private corpus, computing statistics over categorical data and learning embeddings over user-provided items.
We propose an algorithm for this problem, MaxAdaptiveDegree(MAD), which adaptively reroutes weight from items with weight far above the threshold needed for privacy to items with smaller weight, thereby increasing the probability that less frequent items are output. Our algorithm can be efficiently implemented in massively parallel computation systems allowing scalability to very large datasets. We prove that our algorithm stochastically dominates the standard parallel algorithm for this problem. We also develop a two-round version of our algorithm, MAD2R, where results of the computation in the first round are used to bias the weighting in the second round to maximize the number of items output. In experiments, our algorithms provide the best results across the board among parallel algorithms and scale to datasets with hundreds of billions of items, up to three orders of magnitude larger than those analyzed by prior sequential algorithms.
View details
Performance of a Deep Learning Diabetic Retinopathy Algorithm in India
Arthur Brant
Xiang Yin
Lu Yang
Divleen Jeji
Sunny Virmani
Anchintha Meenu
Naresh Babu Kannan
Florence Thng
Lily Peng
Ramasamy Kim
JAMA Network Open (2025)
Preview abstract
Importance: While prospective studies have investigated the accuracy of artificial intelligence (AI) for detection of diabetic retinopathy (DR) and diabetic macular edema (DME), to date, little published data exist on the clinical performance of these algorithms.
Objective: To evaluate the clinical performance of an automated retinal disease assessment (ARDA) algorithm in the postdeployment setting at Aravind Eye Hospital in India.
Design, Setting, and Participants: This cross-sectional analysis involved an approximate 1% sample of fundus photographs from patients screened using ARDA. Images were graded via adjudication by US ophthalmologists for DR and DME, and ARDA’s output was compared against the adjudicated grades at 45 sites in Southern India. Patients were randomly selected between January 1, 2019, and July 31, 2023.
Main Outcomes and Measures: Primary analyses were the sensitivity and specificity of ARDA for severe nonproliferative DR (NPDR) or proliferative DR (PDR). Secondary analyses focused on sensitivity and specificity for sight-threatening DR (STDR) (DME or severe NPDR or PDR).
Results: Among the 4537 patients with 4537 images with adjudicated grades, mean (SD) age was 55.2 (11.9) years and 2272 (50.1%) were male. Among the 3941 patients with gradable photographs, 683 (17.3%) had any DR, 146 (3.7%) had severe NPDR or PDR, 109 (2.8%) had PDR, and 398 (10.1%) had STDR. ARDA’s sensitivity and specificity for severe NPDR or PDR were 97.0% (95% CI, 92.6%-99.2%) and 96.4% (95% CI, 95.7%-97.0%), respectively. Positive predictive value (PPV) was 50.7% and negative predictive value (NPV) was 99.9%. The clinically important miss rate for severe NPDR or PDR was 0% (eg, some patients with severe NPDR or PDR were interpreted as having moderate DR and referred to clinic). ARDA’s sensitivity for STDR was 95.9% (95% CI, 93.0%-97.4%) and specificity was 94.9% (95% CI, 94.1%-95.7%); PPV and NPV were 67.9% and 99.5%, respectively.
Conclusions and Relevance: In this cross-sectional study investigating the clinical performance of ARDA, sensitivity and specificity for severe NPDR and PDR exceeded 96% and caught 100% of patients with severe NPDR and PDR for ophthalmology referral. This preliminary large-scale postmarketing report of the performance of ARDA after screening 600 000 patients in India underscores the importance of monitoring and publication an algorithm's clinical performance, consistent with recommendations by regulatory bodies.
View details
YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks
Saptarashmi Bandyopadhyay
Vikas Bahirwani
Lavisha Aggarwal
Bhanu Guda
Lin Li
Andrea Colaco
2025
Preview abstract
Multimodal AI Agents are AI models that have the capability of interactively and cooperatively assisting human users to solve day-to-day tasks. Augmented Reality (AR) head worn devices can uniquely improve the user experience of solving procedural day-to-day tasks by providing egocentric multimodal (audio and video) observational capabilities to AI Agents. Such AR capabilities can help the AI Agents see and listen to actions that users take which can relate to multimodal capabilities of human users. Existing AI Agents, either Large Language Models (LLMs) or Multimodal Vision-Language Models (VLMs) are reactive in nature, which means that models cannot take an action without reading or listening to the human user's prompts. Proactivity of AI Agents, on the other hand, can help the human user detect and correct any mistakes in agent observed tasks, encourage users when they do tasks correctly, or simply engage in conversation with the user - akin to a human teaching or assisting a user. Our proposed YET to Intervene (YETI) multimodal Agent focuses on the research question of identifying circumstances that may require the Agent to intervene proactively. This allows the Agent to understand when it can intervene in a conversation with human users that can help the user correct mistakes on tasks, like cooking, using Augmented Reality. Our YETI Agent learns scene understanding signals based on interpretable notions of Structural Similarity (SSIM) on consecutive video frames. We also define the alignment signal which the AI Agent can learn to identify if the video frames corresponding to the user's actions on the task are consistent with expected actions. These signals are used by our AI Agent to determine when it should proactively intervene. We compare our results on the instances of proactive intervention in the HoloAssist multimodal benchmark for an expert agent guiding an user agent to complete procedural tasks.
View details
Scalability of Generative AI Models: Challenges and Opportunities in Large-Scale Data Generation and Training
International Journal of Computer Science and Information Technology Research (IJCSITR) (2025)
Preview abstract
Scalability of Generative AI Models: Challenges and Opportunities in Large-Scale Data Generation and Training
View details
Improving simulation-based origin-destination demand calibration using sample segment counts data
Arwa Alanqary
Yechen Li
The 12th Triennial Symposium on Transportation Analysis conference (TRISTAN XII), Okinawa, Japan (2025)
Preview abstract
This paper introduces a novel approach to demand estimation that utilizes partial observations of segment-level track counts. Building on established simulation-based demand estimation methods, we present a modified formulation that integrates sample track counts as a regularization term. This approach effectively addresses the underdetermination challenge in demand estimation, moving beyond the conventional reliance on a prior OD matrix. The proposed formulation aims to preserve the distribution of the observed track counts while optimizing the demand to align with observed path-level travel times. We tested this approach on Seattle's highway network with various congestion levels. Our findings reveal significant enhancements in the solution quality, particularly in accurately recovering ground truth demand patterns at both the OD and segment levels.
View details
Triaging mammography with artificial intelligence: an implementation study
Sarah M. Friedewald
Sunny Jansen
Fereshteh Mahvar
Timo Kohlberger
David V. Schacht
Sonya Bhole
Dipti Gupta
Scott Mayer McKinney
Stacey Caron
David Melnick
Mozziyar Etemadi
Samantha Winter
Alejandra Maciel
Luca Speroni
Martha Sevenich
Arnav Agharwal
Rubin Zhang
Gavin Duggan
Shiro Kadowaki
Atilla Kiraly
Jie Yang
Basil Mustafa
Krish Eswaran
Shravya Shetty
Breast Cancer Research and Treatment (2025)
Preview abstract
Purpose
Many breast centers are unable to provide immediate results at the time of screening mammography which results in delayed patient care. Implementing artificial intelligence (AI) could identify patients who may have breast cancer and accelerate the time to diagnostic imaging and biopsy diagnosis.
Methods
In this prospective randomized, unblinded, controlled implementation study we enrolled 1000 screening participants between March 2021 and May 2022. The experimental group used an AI system to prioritize a subset of cases for same-visit radiologist evaluation, and same-visit diagnostic workup if necessary. The control group followed the standard of care. The primary operational endpoints were time to additional imaging (TA) and time to biopsy diagnosis (TB).
Results
The final cohort included 463 experimental and 392 control participants. The one-sided Mann-Whitney U test was employed for analysis of TA and TB. In the control group, the TA was 25.6 days [95% CI 22.0–29.9] and TB was 55.9 days [95% CI 45.5–69.6]. In comparison, the experimental group's mean TA was reduced by 25% (6.4 fewer days [one-sided 95% CI > 0.3], p<0.001) and mean TB was reduced by 30% (16.8 fewer days; 95% CI > 5.1], p=0.003). The time reduction was more pronounced for AI-prioritized participants in the experimental group. All participants eventually diagnosed with breast cancer were prioritized by the AI.
Conclusions
Implementing AI prioritization can accelerate care timelines for patients requiring additional workup, while maintaining the efficiency of delayed interpretation for most participants. Reducing diagnostic delays could contribute to improved patient adherence, decreased anxiety and addressing disparities in access to timely care.
View details
GOALIE (GOAL oriented IntErventions) Proactive Multimodal Agent to Assist Augmented Reality
Saptarashmi Bandyopadhyay
Vikas Bahirwani
Lavisha Aggarwal
Bhanu Guda
Lin Li
Qin Liu
Tom Goldstein
John Dickerson
Andrea Colaco
2025
Preview abstract
Multimodal AI Agents are helpful to assist and guide users in completing real-time tasks like cooking, robotics, manufacturing. An emerging form of multimodal communication is Augmented Reality (AR), where an AI Agent can enhance user experience with step-by-step guidance of tasks by observing the user's vision and language inputs. Current LLM or VLM based agents are reactive, waiting for an user query before responding. Proactive AI Agents in AR focus on detecting when the AI Agent should autonomously intervene to fix mistakes or followup any instruction. Our GOALIE (GOAL-oriented IntErvention) Agent is the first multimodal proactive AR agent which guides the user step-by-step on its own. We build an innovative Zero-Shot Prompting framework PSoS (Proactive Sequence of Steps) with the context of abstract past user actions, the agent's previous responses, and the user's granular goals and actions before it is detected that the AI Agent should intervene. We use PSoS for Supervised Finetuning (SFT), Direct Preference Optimization (DPO) and Group-Relative Policy Optimization (GRPO) finetuning of our AI agent to improve the quality of the agent's proactive intervention. We also propose a new algorithmic framework, Bagged group Relative Policy Optimization (BRPO), to reduce the variance in rewards of generation groups, to adapt the finetuning algorithm for multimodal proactive interventions by the AI Agent and to enable real-time finetuning of the AI model. We compare the step-by-step intervention quality and efficiency of the GOALIE Agent with Gemma-3 models along with other VLMs for task execution with human expert labels. We conduct human evaluation of the proactive interventions, demonstrating user satisfaction with the GOALIE Agent's proactive interventions. We will release the code, model and human evaluation data.
View details
GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning
Sahiti Yerramilli
Nilay Pande
Rynaa Grover
Jayant Tamarapalli
(2025)
Preview abstract
This paper introduces GeoChain, a large-scale benchmark for evaluating step-by-step geographic reasoning in multimodal large language models (MLLMs). Leveraging 1.46 million Mapillary street-level images, GeoChain pairs each image with a 21-step chain-of-thought (CoT) question sequence (over 30 million Q&A pairs). These sequences guide models from coarse attributes to fine-grained localization across four reasoning categories - visual, spatial, cultural, and precise geolocation - annotated by difficulty. Images are also enriched with semantic segmentation (150 classes) and a visual locatability score. Our benchmarking of contemporary MLLMs (GPT-4.1 variants, Claude 3.7, Gemini 2.5 variants) on a diverse 2,088-image subset reveals consistent challenges: models frequently exhibit weaknesses in visual grounding, display erratic reasoning, and struggle to achieve accurate localization, especially as the reasoning complexity escalates. GeoChain offers a robust diagnostic methodology, critical for fostering significant advancements in complex geographic reasoning within MLLMs.
View details
Preventing Network Bottlenecks: Accelerating Datacenter Services with Hotspot-Aware Placement for Compute and Storage
Hamid Bazzaz
Yingjie Bi
Weiwu Pang
Minlan Yu
Ramesh Govindan
Chloe Tsai
Chris DeForeest
Charlie Carver
Jan Kopański
2025
Preview abstract
Datacenter network hotspots, defined as links with persistently high utilization, can lead to performance bottlenecks.In this work, we study hotspots in Google’s datacenter networks. We find that these hotspots occur most frequently at ToR switches and can persist for hours. They are caused mainly by bandwidth demand-supply imbalance, largely due to high demand from network-intensive services, or demand exceeding available bandwidth when compute/storage upgrades outpace ToR bandwidth upgrades. Compounding this issue is bandwidth-independent task/data placement by data-center compute and storage schedulers. We quantify the performance impact of hotspots, and find that they can degrade the end-to-end latency of some distributed applications by over 2× relative to low utilization levels. Finally, we describe simple improvements we deployed. In our cluster scheduler, adding hotspot-aware task placement reduced the number of hot ToRs by 90%; in our distributed file system, adding hotspot-aware data placement reduced p95 network latency by more than 50%. While congestion control, load balancing, and traffic engineering can efficiently utilize paths for a fixed placement, we find hotspot-aware placement – placing tasks and data under ToRs with higher available bandwidth – is crucial for achieving consistently good performance.
View details
Beyond Digital Literacy: Building Youth Digital Resilience Through Existing “Information Sensibility” Practices
Mia Hassoun
Ian Beacock
Todd Carmody
Patrick Gage Kelley
Beth Goldberg
Devika Kumar
Laura Murray
Rebekah Park
Behzad Sarmadi
Social Sciences Journal, 14(4) (2025)
Preview abstract
Youth media consumption and disordered eating practices have historically been subjects of moral panics, often resulting in protective, deficit-based interventions like content removal. We argue for interventions which instead equip youth to evaluate and manage risks in their online environments, building upon their existing “information sensibility” practices. Drawing upon ethnographic research and intervention testing with 77 participants in the US and India, we analyze how youth (aged 13–26), including those with diverse political perspectives and those recovering from disordered eating (DE), engage with online news and health information. Participants generally algorithmically encountered (rather than searched for) information online, and their engagement was shaped more by social motivations—like belonging—than truth seeking. Participants interpreted online information collaboratively, relying on social cues and peer validation within their online communities. They demonstrated preference for personal testimonies and relatable sources, particularly those with similar social identities. We propose resilience-building interventions that build upon these youth online information practices by: (1) leveraging peer networks, promoting critical information engagement through collaborative learning and peer-to-peer support within online communities; (2) developing social media sensibility, equipping youth to critically evaluate information sources in situ; (3) providing pathways offline, connecting youth to desired in-person communities; and (4) encouraging probabilistic thinking.
View details
I know what I don't know: improving model cascades through confidence tuning
Stephan Rabanser
Nathalie Rauschmayr
Petra Poklukar
Congchao Wang
2025
Preview abstract
Large-scale machine learning models deliver strong performance across a wide range of tasks but come with significant computational and resource constraints. To mitigate these challenges, local smaller models are often deployed alongside larger models, relying on routing and deferral mechanisms to offload complex tasks. However, existing approaches inadequately balance the capabilities of these models, often resulting in unnecessary deferrals or sub-optimal resource usage. In this work we introduce a novel loss function called Gatekeeper for calibrating smaller models in cascade setups. Our approach fine-tunes the smaller model to confidently handle tasks it can perform correctly while deferring complex tasks to the larger model. Moreover, it incorporates a mechanism for managing the trade-off between model performance and deferral accuracy, and is broadly applicable across various tasks and domains without any architectural changes. We evaluated our method on encoder-only, decoder-only, and encoder-decoder architectures. Experiments across image classification, language modeling, and vision-language tasks show that our approach substantially improves deferral performance.
View details
Permission Rationales in the Web Ecosystem: An Exploration of Rationale Text and Design Patterns
Yusra Elbitar
Soheil Khodayari
Marian Harbach
Gianluca De Stefano
Balazs Engedy
Giancarlo Pellegrino
Sven Bugiel
CHI 2025, ACM
Preview abstract
Modern web applications rely on features like camera and geolocation for personalized experiences, requiring user permission via browser prompts. To explain these requests, applications provide rationales—contextual information on why permissions are needed. Despite their importance, little is known about how rationales appear on the web or their influence on user decisions.
This paper presents the first large-scale study of how the web ecosystem handles permission rationales, covering three areas: (i) identifying webpages that use permissions, (ii) detecting and classifying permission rationales, and (iii) analyzing their attributes to understand their impact on user decisions. We examined over 770K webpages from Chrome telemetry, finding 3.6K unique rationale texts and 749 rationale UIs across 85K pages. We extracted key rationale attributes and assessed their effect on user behavior by cross-referencing them with Chrome telemetry data. Our findings reveal nine key insights, providing the first evidence of how different rationales affect user decisions.
View details
Preview abstract
Measuring productivity is equivalent to building a model. All models are wrong, but some are useful. Productivity models are often “worryingly selective” (wrong because of omissions). Worrying selectivity can be combated by taking a holistic approach that includes multiple measurements of multiple outcomes. Productivity models should include multiple outcomes, metrics, and methods.
View details
Context is Key for Agent Security
Lillian Tsai
Eugene Bagdasaryan
arXiv (2025)
Preview abstract
Judging the safety of an action, whether taken by a human or a system, must take into account the context in which the action takes place. For example, deleting an email from a user's mailbox may or may not be appropriate depending on the email's content, the user's goals, or even available space. Systems today that make these judgements---providing security against harmful or inappropriate actions---rely on manually-crafted policies or user confirmation for each relevant context. With the upcoming deployment of systems like generalist agents, we argue that we must rethink security designs to adapt to the scale of contexts and capabilities of these systems. As a first step, this paper explores contextual security in the domain of agents and proposes contextual security for agents (Conseca), a framework to generate just-in-time, contextual, and human-verifiable security policies.
View details
