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 11423 publications
Preview abstract
In modern Kubernetes environments, eBPF (Extended Berkeley Packet Filter) has become the de facto standard for high-performance dataplane enforcement. However, this architecture introduces a complex distributed state problem: the asynchronous synchronization between the Kubernetes control plane (Intent) and the kernel-space BPF maps (Reality).
A critical failure mode, termed “Silent Divergence,” occurs when the control plane believes a network policy or identity is applied, but the underlying kernel state is missing or corrupted. In this “Gray Failure” state, standard observability tools—including logs, liveness probes, and agent status checks—report health, while the network silently drops traffic.
This paper introduces eBPF-Auditor, a specialized consistency verification framework. Unlike standard agents that rely on event-based reconciliation, eBPF-Auditor performs a periodic “Two-Way State Audit” that mathematically verifies the intersection of Kubernetes Intent and BPF Reality. We demonstrate through fault injection and benchmarks on 5,000 pods that this approach successfully detects state drift with 100% accuracy and negligible sub-millisecond overhead (ms), making it a viable solution for high-frequency runtime verification in production hyperscale clusters.
View details
Preview abstract
Online video platforms face an exponential challenge
in detecting and mitigating the flood of AI-generated “slop”
and synthetic spam perpetuated by coordinated malicious actors.
This content is increasingly designed to exploit the limitations
of traditional media forensics, often utilizing generative AI to
produce unique, localized variations of harmful or low-quality
material at scale. Traditional content-centric moderation fails
against this coordinated, adversarial generation strategy.
This paper presents a novel, scalable detection and classifi-
cation framework designed for online video platforms (OVP) to
identify and triage clusters of coordinated accounts exhibiting
a prevalence of adversarial synthetic content. The approach
leverages a multi-faceted architecture incorporating two core
machine learning components: a robust Coordinated Bot-Net
Detector (via Account Relatedness) and a Synthetic Pattern Clas-
sifier. Crucially, we introduce an advanced AI enhancement layer
utilizing Large Language Models (LLMs), specialized via Low-
Rank Adaptation (LoRA) and Automatic Prompt Optimization
(APO), to achieve rapid, high-precision semantic understanding
of emerging synthetic spam trends.
Evaluated across a representative evaluation dataset (N =
16, 250 weekly candidate channels across six major synthetic
abuse verticals), the system demonstrates high precision (FPR <
0.05%) in identifying coordinated synthetic spam networks.
Furthermore, the LLM-driven classification achieves a 74%
automated triage routing rate, saving over 1, 100 operational
review hours per week while reducing investigation turnaround
times by up to 50% (p < 0.001). This work details a critical
system design that provides essential scalability and adversarial
resilience against sophisticated generative attacks.
View details
Preview abstract
Config Driven User Interface (CDUI) frameworks, often referred to interchangeably as
Server Driven UI (SDUI) have fundamentally altered mobile and web application development. By shifting layout and orchestration logic from compiled client binaries to dynamic
server responses, organizations bypass slow app store review cycles and ensure cross-platform
consistency. Despite its widespread adoption by industry leaders, CDUI remains underexplored in formal software engineering literature. This paper investigates the evolution of
CDUI through a hybrid methodology, combining a Multivocal Literature Review (MLR) of
grey literature from organizations including Uber, Airbnb, Lyft, Spotify, Faire, and Zalando,
with a structural artifact analysis of open-source production frameworks (Yandex DivKit,
Zup Beagle, and Spotify Hub). We introduce a taxonomy grounded in established foundational UI components and evaluate systems across three axes: Modularity, Centralization,
and Strictness. By tracing the architectural evolution from simple remote configurations to
strongly typed, Protobuf-driven contracts, our empirical artifact analysis (evaluating 570
schema commits across three repositories) demonstrates the critical magnitude of schema
governance and the complex challenge of managing “contract fragility.” We further analyze
cross-cutting concerns such as security sandboxing, “BFF Bloat,” and native accessibility
mapping, culminating in a future research agenda focused on the formal verification of UI
configurations.
View details
Securing Multi-Agent Systems: An Empirical Analysis of Security Prompt Hardening and Residual Risks
Mithil Roshan
Shashank Nagesh
(2026)
Preview abstract
The rapid adoption of agentic systems powered by
large language models (LLMs) introduces significant
security challenges distinct from plain conversational
models, particularly concerning prompt injection and
tool misuse due to their dynamic personas and real-
world tool interactions. This paper investigates the
effectiveness of hardened security prompting in a
task-oriented multi-agent framework, using a coding
assistant as a representative case study. We com-
pare a baseline ”unhardened” agent against a ”hard-
ened” version equipped with explicit security guide-
lines applied across all sub-agents. Our evaluation
across 150+ single-turn and 32 multi-turn attack sce-
narios demonstrates that prompt hardening dramat-
ically improves resilience. With a simple, approxi-
mately 500-token security hardener, single-turn fail-
ure rates dropped from 19.48% to 2.60%, while multi-
turn failure rates decreased from 75.00% to 46.88%.
Furthermore, we show that successfully bypassing the
hardened agent requires significantly more adversar-
ial effort and a greater number of chat turns. How-
ever, the analysis also reveals a critical shift in vul-
nerability taxonomy: as direct attacks fail, adver-
saries exploit the agent’s core functionality via ”Func-
tional Wrappers” (Intent Obfuscation), highlighting
a residual risk that necessitates a shift in the defen-
sive paradigm from static filters to dynamic runtime
state and intent analysis.
View details
Preview abstract
In some multi-stage software build pipelines, downstream compiler errors may be reported against ephemeral, machine-generated intermediate artifacts rather than original, human-written source code, which can make remediation challenging. A system and method may address this by intercepting a downstream error, mapping its location back to the original source file, and programmatically injecting a dormant suppression tag into the original source code. During a subsequent build, an intermediate transpiler can propagate this tag into a newly generated intermediate artifact. In the intermediate file, the tag may become active and be recognized by the downstream compiler as a directive to suppress the specific error. This approach can facilitate an automated remediation process for certain build failures that avoids direct modification of ephemeral files and uses the original source code as a record for suppression.
View details
CSIG: Congestion Signaling for Datacenter Transports
Abhiram Ravi
Brad Karp
MJ Akhbari
Weida Huang
Konstantinos Prasopoulos
2026
Preview abstract
Optimizing burst-heavy datacenter workloads necessitates fine-grained network control and visibility. We introduce CSIG, a protocol that delivers precise, multi-bit bottleneck congestion signals via a fixed-length Ethernet header. The architecture captures 𝜇s-granularity switch metrics, such as available bandwidth, and signals them to end-hosts using in-band, line-rate operations. We propose Fast Ramp-Up, a congestion control primitive that leverages these bottleneck signals to reduce median RPC latency by 20% and unclaimed bandwidth by 60% in production. Beyond transport-level performance, CSIG enables flow-aware observability by embedding 𝜇s-scale metrics into every packet, allowing individual application transfers to pinpoint their bottleneck location, such as the topology tier limiting their performance. CSIG thus transforms network telemetry from post-hoc correlation into a real time, contextaware capability. We demonstrate CSIG’s broad deployability by validating it across five generations of commodity switch hardware (up to 102.4 Tbps), four NIC generations, and five transport stacks. Our design proves that a streamlined Layer 2 approach, focusing exclusively on the principal path bottleneck, provides transport-agnostic gains without requiring forklift hardware upgrades.
View details
Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction
Proceedings of the 43rd International Conference on Machine Learning (ICML 2026)
Preview abstract
A fundamental dichotomy in the theory of classification sets smoothness against statistical efficiency: smooth surrogate losses such as the logistic loss enable fast $O(1/T)$ optimization but yield slow square-root $H$-consistency bounds, while piecewise-linear losses like the Hinge loss achieve optimal linear $H$-consistency rates but are non-differentiable. We introduce Linear-Core (LC) Surrogates, the first family of explicit convex loss functions that provably resolve this tension. By stitching a linear core to a smooth tail, we construct surrogates that are differentiable everywhere ($C^1$, and even $C^2$ under mild conditions) while retaining strict linear $H$-consistency bounds, the strongest known form of consistency guarantee. We establish these linear bounds across three increasingly complex settings: binary classification, multi-class classification, and structured prediction. To our knowledge, this is the first explicit construction to simultaneously achieve smoothness and linear $H$-consistency in any of these settings. Beyond their theoretical appeal, Linear-Core Surrogates offer practical advantages. In multi-class classification, their constant gradient profile near the decision boundary provides natural robustness to instance-dependent label noise, outperforming Cross-Entropy by 2.6% on corrupted CIFAR-10. In structured prediction, their smoothness enables an unbiased stochastic gradient estimator that bypasses the $O(|Y|^2)$ per-step complexity of exact inference, yielding a 23$\times$ speedup over Structured SVMs on large-vocabulary sequence tagging tasks.
View details
Preview abstract
In a prior column, we wrote about how measuring productivity can be viewed as a form of modeling and that all models are wrong, but some are useful. That discussion centered on the idea of ensuring that a productivity model was inclusive of multiple metrics and that those metrics covered the various facets of productivity and covered each facet reasonably well. In that article, we set aside the question of what makes a good individual productivity metric that can be combined with others into a (hopefully) useful model of productivity. In this article, we’ll share some things we consider when building an individual metric, including an example of a novel metric we built in the aftermath of the COVID pandemic.
View details
CoDaS: AI Co-Data-Scientist for Biomarker Discovery via Wearable Sensors
Juro Gottweis
CJ Park
Salman Rahman
Ahmed Metwally
Hong Yu
Ivor Rendulic
Yuzhe Yang
Petar Sirkovic
Daniel McDuff
Shwetak Patel
Nicolas Stroppa
Yubin Kim
Mark Malhotra
Orson Xu
Sam Schmidgall
Tim Althoff
Elahe Vedadi
Cynthia Breazeal
Hae Won Park
(2026)
Preview abstract
Large language models (LLMs) are increasingly deployed as economic agents in marketplaces, auctions, and bidding settings. Anticipating their behavior in any specific deployment is hard. Existing strategic-reasoning benchmarks evaluate models on fixed canonical games. These benchmarks may saturate as the frontier improves, and they do not allow evaluators to generalize with confidence from benchmark performance to the varied and messy strategic environments that actual deployments involve. We introduce GENSTRAT, which uses procedurally generated strategic environments to address these challenges. Concretely, we generate a distribution of two-player zero-sum imperfect-information card games. The generator can draw fresh games on demand, allowing for evergreen evaluation and resistance to contamination. We pair the game distribution with a capability-profile methodology that decomposes model competence across six axes (state space, temporal depth, information sensitivity, opponent modeling, risk, and brittleness). We also introduce a jaggedness measure of within-distribution smoothness that detects when a model’s advantage jumps unpredictably between strategically similar games. We sample 50 benchmark games from a 2,000-game generated pool and evaluate nine frontier and open-weight LLMs in a head-to-head tournament with over 36,000 matches. Newer frontier-tier models score higher on average. Beyond that average, models with near-identical overall strength show qualitatively different capability profiles, and two of the top three leaderboard models (gpt-5 and claude) are noticeably more locally volatile than the third (gemini-3.1-pro), despite being close in overall strength. Together, the capability profile and the jaggedness measure give a deployment-relevant diagnostic that the overall ranking alone cannot provide.
View details
Preview abstract
This study examines the psychological and ethical implications of generative-AI chatbot use among youth, introducing the CTRL framework (Cognitive Trust, Reliance, and Learning Diminution) to explain how repeated use fosters cognitive offloading and reduced verification behavior. Survey data from 420 participants analyzed through factor analysis and structural equation modeling reveal that higher trust predicts greater reliance and diminished critical evaluation, alongside elevated concerns around privacy and academic integrity. Findings highlight the need for AI literacy and responsible design to mitigate unintended cognitive impacts.
View details
Preview abstract
Advancements in large language models (LLMs) have made them increasingly useful for complex reasoning tasks which previously required domain experts. One such task is quality evaluation of query responses produced by a search engine. Evaluation generates metrics necessary to study the quality, impact, and usefulness of product changes and features. Typically, to compute evaluation metrics, human experts are asked to rate various attributes of search responses. This process is generally quite expensive and requires several days to complete. As an alternative, LLMs are now being used to perform rating tasks with lower costs and latency. In addition, many new metrics are being developed to evaluate Google's new AI-based offerings, which require ratings too. As a result, there is much higher demand for LLM rating prediction tasks in comparison with the allocated TPU (Tensor Processing Unit) budget. A larger portion of the company's TPU resources are reserved for serving live user traffic. In this paper, we present the AI Rater Service (AIRS), an inference pipeline that employs several software engineering techniques to generate AI ratings with high reliability and low latency. AIRS maximizes LLM inference throughput by optimizing TPU resource utilization across various evaluation workflows, while minimizing latency for higher priority tasks.
View details
Generational differences in anthropomorphism and trust calibration for large language models
Michelle Cohn
Joscelin Cooper
Femi Olanubi
Zion Mengesha
Frontiers in Cognition (2026)
Preview abstract
This paper examines how English-speaking adults in the United States (n=1530) anthropomorphize and calibrate trust for a pseudo-large language model (LLM). We compared four generations: Gen Z (age 18-26), Millennials (age 27-43), Gen X (age 44-57), and Baby Boomers (age 58-78). The LLM varied in cues of anthropomorphism: whether the system responded in text-only or text and speech, as well as whether it used the first-person singular (“I”) or third-person singular (“The system”) in its responses. Across both types of manipulations, results showed that Gen Z, in particular, showed consistently lower anthropomorphism (less competent, human-like, natural, conscious, life-like), reduced trust ratings of the system, and lower ratings of accuracy for responses generated by the LLM. Furthermore, we saw that the likelihood to externally validate the LLM’s response varied across the generations across contexts, where Baby Boomers were more likely to validate information about medication and health disorders and Gen Z about cooking. We did not see an interaction between the generations and the anthropomorphic cues manipulated; rather, there was a consistent increase in anthropomorphism and perceived accuracy for systems that used speech + text, relative to text only. There were no across-the-board effects of the first-person singular. We discuss these findings in terms of their implications for responsible AI.
View details
TDXRay: Microarchitectural Side-Channel Analysis of Intel TDX for Real-World Workloads
Tristan Hornetz
Hosein Yavarzadeh
Albert Cheu
Adria Gascon
Lukas Gerlach
Michael Schwarz
Ruiyi Zhang
IEEE Security & Privacy (S&P) (2026)
Preview abstract
Confidential computing with VM-based trusted execution environments (TEEs) promises to protect code and data from a privileged cloud operator, enabling privacy-preserving workloads ranging from medical analytics to AI inference. However, most deployments exclude microarchitectural side channels from their threat model, shifting the burden to application developers who lack practical, general-purpose tools to assess (let alone mitigate) leakage. This gap is problematic: host-observable effects such as page-fault patterns, shared-cache contention, performance-counter surrogates (where available), and fine-grained timing primitives (e.g., MWAIT) can still reveal high-level secrets even when memory remains encrypted.
We present TDXRay, an open-source framework that systematizes the evaluation of side-channel risk for confidential VMs in Intel TDX. TDXRay exposes unified interfaces to exercise and measure several attack primitives—including controlled-channel attacks via page tables, cache-based contention/occupancy probes, performance-counter–derived signals, and timing channels—against unmodified guest workloads. Using TDXRay, we build two end-to-end case studies: (1) a classic AES T-table attack in which a malicious hypervisor recovers the secret key from access-pattern leakage, and (2) an LLaMA inference attack in which the host infers user prompts by monitoring memory accesses during tokenization and embedding lookups. Across both, we show that a host with no direct access to guest memory can reconstruct sensitive information by observing only externalized microarchitectural signals.
View details
Preview abstract
We prove the following asymptotically tight lower bound for k-color discrepancy: For any k ≥ 2, there exists a hypergraph with n vertices such that its k-color discrepancy is at least Ω(√n). This improves on the previously known lower bound of Ω(√n/ log k) due to Caragiannis et al. [CLS25]. As an application, we show that our result implies improved lower bounds for group fair division.
View details
