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 10407 publications
AI Agents for Cloud Reliability: Autonomous Threat Detection and Mitigation Aligned with Site Reliability Engineering Principles
Preview
Karan Anand
Mourya Chigurupati
2025
Quartic Quantum Speedups for Planted Inference Problems
Alexander Schmidhuber
Ryan O'Donnell
Physical Review X, 15 (2025), pp. 021077
Preview abstract
We describe a quantum algorithm for the Planted Noisy kXOR problem (also known as sparse Learning Parity with Noise) that achieves a nearly quartic (4th power) speedup over the best known classical algorithm while also only using logarithmically many qubits. Our work generalizes and simplifies prior work of Hastings, by building on his quantum algorithm for the Tensor Principal Component Analysis (PCA) problem. We achieve our quantum speedup using a general framework based on the Kikuchi Method (recovering the quartic speedup for Tensor PCA), and we anticipate it will yield similar speedups for further planted inference problems. These speedups rely on the fact that planted inference problems naturally instantiate the Guided Sparse Hamiltonian problem. Since the Planted Noisy kXOR problem has been used as a component of certain cryptographic constructions, our work suggests that some of these are susceptible to super-quadratic quantum attacks.
View details
Scaling Laws for Downstream Task Performance in Machine Translation
Natalia Ponomareva
Hussein Hazimeh
Sanmi Koyejo
International Conference on Learning Representations (ICLR) (2025) (to appear)
Preview abstract
Scaling laws provide important insights that can guide the design of large language models (LLMs). Existing work has primarily focused on studying scaling laws for pretraining (upstream) loss. However, in transfer learning settings, in which LLMs are pretrained on an unsupervised dataset and then finetuned on a downstream task, we often also care about the downstream performance. In this work, we study the scaling behavior in a transfer learning setting, where LLMs are finetuned for machine translation tasks. Specifically, we investigate how the choice of the \emph{pretraining} data and its size affect downstream performance (translation quality) as judged by: downstream cross-entropy and translation quality metrics such as BLEU and COMET scores. Our experiments indicate that the size of the finetuning dataset and the distribution alignment between the pretraining and downstream data significantly influence the scaling behavior. With sufficient alignment, both downstream cross-entropy and translation quality scores improve monotonically with more pretraining data. In such cases, we show that it is possible to predict the downstream translation quality metrics with good accuracy using a log-law. However, there are cases where moderate misalignment causes the downstream translation scores to fluctuate or get worse with more pretraining, whereas downstream cross-entropy monotonically improves. By analyzing these, we provide new practical insights for choosing appropriate pretraining data.
View details
Leveraging Per-Example Privacy for Machine Unlearning
Nazanin Mohammadi Sepahvand
Anvith Thudi
Ashmita Bhattacharyya
Nicolas Papernot
Eleni Triantafillou
Daniel M. Roy
Karolina Dziugaite
International Conference on Machine Learning (ICML) (2025)
Preview abstract
This work focuses on developing fine-grained theoretical insights to quantify unlearning difficulty at the level of individual data points for fine-tuning-based unlearning. Unlike other unlearning methods that lack theoretical guarantees for non-convex models, our approach builds on recent advances in differential privacy to provide per-instance guarantees using Rényi divergence. While our theoretical analysis applies to Langevin dynamics, we empirically demonstrate that the derived guarantees—and their trends—continue to hold for fine-tuning, even in the absence of explicit noise. Our results show that per-instance privacy levels computed from training dynamics reliably predict unlearning difficulty, offering a principled and practical way to assess unlearning performance. Furthermore, our method identifies harder-to-unlearn data more effectively than existing heuristics, providing a more precise tool for guiding unlearning strategies. These findings pave the way for adaptive and efficient unlearning methods tailored to the properties of specific data points.
View details
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
Preview abstract
Cloud platforms have been virtualizing storage devices like flash-based solid-state drives (SSDs) to make effective use of storage resources. They enable either software-isolated instance or hardware-isolated instance for facilitating the storage sharing between multi-tenant applications. However, for decades, they have to combat the fundamental tussle between the performance isolation and resource utilization. They suffer from either long tail latency caused by weak isolation or low storage utilization caused by strong isolation.
In this paper, we present FleetIO, a learning-based storage virtualization framework that employs reinforcement learning (RL) for managing virtualized SSDs. FleetIO explores the unique features of RL to handle the dynamic changes of application workloads and storage states, and integrates the storage scheduling into the RL decision-making process. It achieves both performance isolation and improved storage utilization by enabling dynamic fine-grained storage harvesting across co-located application instances, while minimizing its negative impact on their service-level objectives (SLOs). FleetIO clusters workloads into different types (e.g., latency-sensitive and bandwidth-intensive) based on the collected I/O traces at runtime, and fine-tunes the RL reward functions for each type of workloads. We implement FleetIO on a real programmable SSD board and evaluate it with diverse cloud applications. We show that FleetIO improves the overall storage utilization of the shared SSD by up to 1.4×, and decreases the tail latency of I/O requests by 1.5× on average, compared to the state-of-the-art storage sharing approaches.
View details
Preview abstract
Creativity in software development is frequently overlooked, specifically
in the design of developer tools which often focus on productivity. This is likely
because creativity is not always seen as a goal in software engineering; in part,
this can be explained by the unique way in which software engineers relate to
creativity as centered around reusability rather than novelty. However, creativity is
a critical aspect of software engineering, and importantly, there is a clear
possibility for AI to impact creativity in both positive or negative ways. In this
article, we explore the differences in goals for designing AI tools for productivity
compared to creativity and propose strategies to elevate creativity in the software
engineering workflow. Specifically, we apply seamful design to AI powered
software development to consider the role of seamfulness in software
development workflows as a way to support creativity.
View details
Ransomware over Modern Web Browsers: A Novel Strain and A New Defense Mechanism
Harun Oz
Ahmet Aris
Leonardo Babun
Selcuk Uluagac
Abbas Acar
ACM Transactions on the Web (2025)
Preview abstract
Ransomware is an increasingly prevalent form of malware targeting end-users, governments, and businesses. As it has evolved,
adversaries added new capabilities to their arsenal. Throughout the ransomware evolution, the adversaries propose a next-generation
browser-based ransomware, RøB, that performs its malicious actions via emerging web technologies, File System Access API (FSA) and
WebAssembly (Wasm). RøB uses this API through the victims’ browsers; hence, it does not require the victims to download and install
malicious binaries. We performed extensive evaluations with 3 different OSs, 23 file formats, 29 distinct directories, 5 cloud providers,
and 4 antivirus solutions. Our evaluations show that RøB can encrypt various types of files in the local and cloud-integrated directories,
external storage devices, and network-shared folders of victims. Our experiments also reveal that popular cloud solutions, Box
Individual and Apple iCloud can be severely affected by RøB. Moreover, we conducted tests with commercial antivirus software such
as AVG, Avast, Kaspersky, Malware Bytes that perform sensitive directory and suspicious behavior monitoring against ransomware.
We verified that RøB can evade these antivirus software and encrypt victim files. Moreover, existing ransomware detection solutions
in the literature also cannot be a remedy against RøB due to its distinct features. Therefore, in this paper, we also propose broguard,
a new detection system for RøB-like attacks. broguard monitors the web applications that use the FSA API via function hooking and
uses a machine learning classifier to detect RøB-like attacks in real-time without any file loss. Performance evaluations of broguard
on a comprehensive dataset show that broguard can detect RøB-like browser-based ransomware attacks with over 99% accuracy and
minimal overhead.
View details
Mufu: Multilingual Fused Learning for Low- Resource Translation with LLM
Zheng Lim
Honglin Yu
Trevor Cohn
International Conference on Learning Representations (ICLR) 2025
Preview abstract
Multilingual large language models (LLMs) are great translators, but this is largely limited to high-resource languages. For many LLMs, translating in and out of low-resource languages remains a challenging task. To maximize data efficiency in this low-resource setting, we introduce Mufu, which includes a selection of automatically generated multilingual candidates and an instruction to correct inaccurate translations in the prompt. Mufu prompts turn a translation task into a postediting one, and seek to harness the LLM's reasoning capability with auxiliary translation candidates, from which the model is required to assess the input quality, align the semantics cross-lingually, copy from relevant inputs and override instances that are incorrect. Our experiments on En-XX translations over the Flores-200 dataset show LLMs finetuned against Mufu-style prompts are robust to poor quality auxiliary translation candidates, achieving performance superior to NLLB 1.3B distilled model in 64% of low- and very-low-resource language pairs. We then distill these models to reduce inference cost, while maintaining on average 3.1 chrF improvement over finetune-only baseline in low-resource translations.
View details
Capturing Real-World Habitual Sleep Patterns with a Novel User-centric Algorithm to Pre-Process Fitbit Data in the All of Us Research Program: Retrospective observational longitudinal study
Hiral Master
Jeffrey Annis
Karla Gleichauf
Lide Han
Peyton Coleman
Kelsie Full
Neil Zheng
Doug Ruderfer
Logan Schneider
Evan Brittain
Journal of Medical Internet Research (2025) (to appear)
Preview abstract
Background:
Commercial wearables like Fitbits quantify sleep metrics using fixed calendar times as the default measurement periods, which may not adequately account for individual variations in sleep patterns. To address this, experts in sleep medicine and wearables developed a user-centric algorithm that more accurately reflects actual sleep behaviors, aiming to improve wearable-derived sleep metrics.
Objective:
The study aimed to describe the development of the new (user-centric) algorithm, and how it compares with the default (calendar-relative), and offers best practices for analyzing All of Us Fitbit sleep data on a cloud platform.
Methods:
The default and new algorithms was implemented to pre-process and then compute sleep metrics related to schedule, duration, and disturbances using high-resolution Fitbit sleep data from 8,563 participants (median age 58.1 years, 72% female) in the All of Us Research Program (v7 Controlled Tier). Variation in typical sleep patterns was computed by taking the differences in the mean number of primary sleep logs classified by each algorithm. Linear mixed-effects models were used to compare differences in sleep metrics across quartiles of variation in typical sleep patterns.
Results:
Out of 8,452,630 total sleep logs over a median of 4.2 years of Fitbit monitoring, 401,777 (5%) non-primary sleep logs identified by default algorithm were reclassified to primary sleep by the user-centric algorithm. Variation in typical sleep patterns ranged from -0.08 to 1. Among participants with the most variation in typical sleep patterns, the new algorithm identified more total sleep time (by 17.6 minutes; P<0.001), more wake after sleep onset (by 13.9 minutes; P<0.001), and lower sleep efficiency (by 2.0%; P<0.001), on average. There were only modest differences in sleep stage metrics between the two algorithms.
Conclusions:
The user-centric algorithm captures the natural variability in sleep schedules, offering an alternative way to pre-process and evaluate sleep metrics related to schedule, duration, and disturbances. R package is publicly available to facilitate the implementation of this algorithm for clinical and translational use.
View details
Opportunities and Applications of GenAI in Smart Cities: A User-Centric Survey
Shashank Kapoor
Aman Raj
2025
Preview abstract
The proliferation of IoT in cities, combined with Digital Twins, creates a rich data foundation for Smart Cities aimed at improving urban life and operations. Generative AI (GenAI) significantly enhances this potential, moving beyond traditional AI analytics by processing multimodal content and generating novel outputs like text and simulations. Using specialized or foundational models, GenAI's natural language abilities such as Natural Language Understanding (NLU) and Generation (NLG) can power tailored applications and unified interfaces, dramatically lowering barriers for users interacting with complex smart city systems. In this paper, we focus on GenAI applications based on conversational interfaces within the context of three critical user archetypes in a Smart City - Citizens, Operators and Planners. We identify and review GenAI models and techniques that have been proposed or deployed for various urban subsystems in the contexts of these user archetypes. We also consider how GenAI can be built on the existing data foundation of official city records, IoT data streams and Urban Digital Twins. We believe this work represents the first comprehensive summarization of GenAI techniques for Smart Cities from the lens of the critical users in a Smart City.
View details
Preview abstract
Given copies of a quantum state $\rho$, a shadow tomography protocol aims to learn all expectation values from a fixed set of observables, to within a given precision $\epsilon$. We say that a shadow tomography protocol is \textit{triply efficient} if it is sample- and time-efficient, and only employs measurements that entangle a constant number of copies of $\rho$ at a time. The classical shadows protocol based on random single-copy measurements is triply efficient for the set of local Pauli observables. This and other protocols based on random single-copy Clifford measurements can be understood as arising from fractional colorings of a graph $G$ that encodes the commutation structure of the set of observables. Here we describe a framework for two-copy shadow tomography that uses an initial round of Bell measurements to reduce to a fractional coloring problem in an induced subgraph of $G$ with bounded clique number. This coloring problem can be addressed using techniques from graph theory known as \textit{chi-boundedness}. Using this framework we give the first triply efficient shadow tomography scheme for the set of local fermionic observables, which arise in a broad class of interacting fermionic systems in physics and chemistry. We also give a triply efficient scheme for the set of all $n$-qubit Pauli observables. Our protocols for these tasks use two-copy measurements, which is necessary: sample-efficient schemes are provably impossible using only single-copy measurements. Finally, we give a shadow tomography protocol that compresses an $n$-qubit quantum state into a $\poly(n)$-sized classical representation, from which one can extract the expected value of any of the $4^n$ Pauli observables in $\poly(n)$ time, up to a small constant error.
View details
AI as a Catalyst for Educational Equity: Addressing Global Teacher Shortages and Learning Disparities
International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCERT) (2025)
Preview abstract
The global education system is grappling with a critical shortage of teachers, threatening the achievement of universal quality education. This article examines how artificial intelligence (AI) technologies can revolutionize educational access and equity by addressing these systemic challenges. Through a comprehensive article analysis of AI-enabled solutions, including personalized learning mechanisms, virtual tutoring systems, and intelligent content distribution platforms, the article explores the transformative potential of these technologies in democratizing education. The article investigates the implementation of AI across established educational platforms, examining their effectiveness in providing adaptive learning experiences, breaking down language barriers, and ensuring cultural relevance. The article demonstrates that strategic AI integration can significantly impact learning outcomes while helping to bridge the global teacher shortage gap. The article also addresses critical implementation challenges, providing policy recommendations and resource allocation frameworks for successful AI adoption in education systems worldwide. This article analysis contributes to the growing body of knowledge on educational technology by offering practical insights into how AI can be leveraged to create more inclusive, effective, and accessible learning environments, ultimately advancing the goal of quality education for all.
View details
HueManity: Probing Fine-Grained Visual Perception in MLLMs
Rynaa Grover
Jayant Tamarapalli
Sahiti Yerramilli
Nilay Pande
(2025)
Preview abstract
Multimodal Large Language Models (MLLMs) excel at high-level visual reasoning, but their performance on nuanced perceptual tasks remains surprisingly limited. We present HueManity, a benchmark designed to assess visual perception in MLLMs. The dataset comprises 83,850 images featuring two-character alphanumeric strings embedded in Ishihara test style dot patterns, challenging models on precise pattern recognition. Our evaluation of nine state-of-the-art MLLMs on HueManity demonstrates a significant performance deficit compared to human and traditional computer vision baselines. The best-performing MLLM achieved a 33.6% accuracy on the numeric "easy" task and a striking 3% on the alphanumeric "hard" task. In contrast, human participants achieved near-perfect scores (100% and 95.6%), and a fine-tuned ResNet50 model reached accuracies of 96.5% and 94.5%. These results highlight a critical gap in the visual capabilities of current MLLMs. Our analysis further explores potential architectural and training-paradigm factors contributing to this perceptual gap in MLLMs. We will open-source HueManity dataset and code to foster further research in improving perceptual robustness of MLLMs.
View details
Preview abstract
Despite the advent of legislation such as the General Data Protection Regulation (GDPR) with its associated "Right to be Forgotten" (RTBF), few, if any, studies have measured user reactions to realistic edge cases with public-interest content. Surveying both users covered by and excluded from RTBF, this vignette-based survey experiment sought to better understand how users think of delisting content from search engine results and what factors influence user perceptions. While leaving information accessible in search engine results generally leads to warmer feelings towards those search engines than delisting it, we find that users do prefer different outcomes
depending on contextual elements specific to given cases. We also find that whether a country has active RTBF legislation does seem to be associated with both knowledge and attitudes about RTBF, but is unlikely to explain all of it. These results indicate a complex context around removing public-interest content from search engines’ results; it is essential that experts sensitive to local context perform the review in order to ensure that removal requests are handled in a way that meets users’ expectations.
View details