arXiv:2607.07923v1 Announce Type: new
Abstract: We study robust high-order time splittings for nonlinear Schr\"odinger equations whose linear part is defined by the Laplacian and an arbitrary three-dimensional rotation operator. After Fourier pseudospectral discretization, a continuous exact factorization of the linear flow need not yield a method self-adjoint fixed-grid propagator. For the original stage-wise explicit exact integrator, we identify a quadratic even term in the local logarithm and show that its visibility is state-dependent, so the observed temporal order of accuracy can depend on the initial data. We then formulate fixed-grid admissibility for discrete linear propagators and construct two admissible propagators for arbitrary three-dimensional rotation: a symmetrized explicit exact integrator and a palindromic generalized shear propagator. Both are unitary, first-order consistent, method self-adjoint, and have odd local logarithms. Numerical experiments verify the predicted defect mechanism and demonstrate recovery of the designed second-, fourth-, and sixth-order behavior with the admissible propagators.
Science Journals
arXiv:2607.07926v1 Announce Type: new
Abstract: Control-flow attestation (CFA) enables a remote entity to verify program execution on a target device by monitoring control-flow behaviour at runtime. However, control-flow bending (CFB) attacks remain difficult to detect, where an adversary steers execution along legal edges of the program's control-flow graph by corrupting branch flags, loop counters, and other runtime data. Existing solutions impose significant drawbacks: they require enumerating vast measurement spaces, cover only a reduced subset of attacks, or rely on low-level hardware modifications. In this work, we present KS-CFA, a new CFA scheme that detects CFB attacks across four transfer types (indirect calls, conditional and indirect jumps, and returns) without those costs. To this end, we combine symbolic execution and selective identification of input-sourced control-flow dependent variables: a strict subset of control-flow-relevant state whose values are directly read from external input. The proving device records, inside a trusted execution environment (TEE), a control-flow trace and the external inputs that determine relevant run-time variables. The verifier then replays the reported path through single-path symbolic execution, predicting each transfer and localising divergences that signal an attack. We implement and evaluate KS-CFA using the RISC-V Keystone TEE and Embench-IoT on QEMU and a Rocket-based FPGA platform (NiteFury II). Prover-side overhead relative to unattested execution ranges from 6.8-20.5x on QEMU and 6.7-32.2x on the FPGA, and verification requires no path or value enumeration.
arXiv:2202.13142v3 Announce Type: replace
Abstract: A key challenge of real-world image super-resolution (SR) is to recover the missing details in low-resolution (LR) images with complex unknown degradations (e.g., downsampling, noise and compression). Most previous works restore such missing details in the image space. To cope with the high diversity of natural images, they either rely on the unstable GANs that are difficult to train and prone to artifacts, or resort to explicit references from high-resolution (HR) images that are usually unavailable. In this work, we propose Feature Matching SR (FeMaSR), which restores realistic HR images in a much more compact feature space. Unlike image-space methods, our FeMaSR restores HR images by matching distorted LR image features to their distortion-free HR counterparts in our pretrained HR priors, and decoding the matched features to obtain realistic HR images. Specifically, our HR priors contain a discrete feature codebook and its associated decoder, which are pretrained on HR images with a Vector Quantized Generative Adversarial Network (VQGAN). Notably, we incorporate a novel semantic regularization in VQGAN to improve the quality of reconstructed images. For the feature matching, we first extract LR features with an LR encoder consisting of several Swin Transformer blocks and then follow a simple nearest neighbour strategy to match them with the pretrained codebook. In particular, we equip the LR encoder with residual shortcut connections to the decoder, which is critical to the optimization of feature matching loss and also helps to complement the possible feature matching errors. Experimental results show that our approach produces more realistic HR images than previous methods. Codes are released at https://github.com/chaofengc/FeMaSR.
arXiv:2204.04883v2 Announce Type: replace
Abstract: With the advent of the cloud computing era, the cost of creating, capturing, and managing information has gradually decreased. The amount of data on the Internet is showing explosive growth, and more scientific and technological resources are being uploaded to the network. Different from news and social media data, scientific and technological resources are mainly composed of academic-style resources or entities, such as papers, patents, authors, and research institutions. There is a rich relationship network between these resources, from which a large amount of cutting-edge scientific and technological information can be mined. Existing scientific resource management and classification standards are difficult to completely cover all entities and associations, and they cannot accurately extract the important information contained in scientific and technological resources. Therefore, how to construct a complete and accurate representation of scientific and technological resources from structured and unstructured reports and texts, and how to tap the potential value of scientific and technological resources, are urgent problems. A feasible solution is to construct accurate portraits of scientific and technological resources by combining knowledge graph technology, text representation learning, entity extraction, and knowledge service components.
arXiv:2510.22052v2 Announce Type: replace
Abstract: The field of artificial intelligence (AI) has taken a tight hold on broad aspects of society, industry, business, and governance in ways that dictate the prosperity and might of the world's economies. The AI market size is projected to grow from {\$}189 billion in 2023 to {\$}4.8 trillion by 2033. Currently, AI is dominated by large language models (LLMs) that exhibit linguistic and visual intelligence. However, training these models requires a massive amount of data scraped from the web as well as large amounts of energy (50-60 GWh to train GPT-4). Despite these costs, these models often hallucinate, a characteristic that prevents them from being deployed in critical application domains. In contrast, the human brain consumes only 20W of power. What is needed is the next level of AI evolution in which lightweight domain-specific multimodal models, especially compact models with 10--20B parameters for bounded domains, with higher levels of intelligence can reason, plan, and make decisions in dynamic environments with real-time data and prior knowledge, while learning continuously and evolving in ways that enhance future decision-making capability. This will define the next wave of AI, progressing from today's large models, trained with vast amounts of data, to nimble energy-efficient domain-specific agents that can reason and think in a world full of uncertainty. To support such agents, hardware will need to be reimagined to allow system-level energy efficiencies $\geq {1000X}$ over the state of the art for targeted domain tasks, subject to accuracy, latency, and coverage constraints. Such a vision of future AI systems is developed in this work.
arXiv:2204.04888v2 Announce Type: replace
Abstract: In recent years, with the continuous progress of science and technology, the number of scientific research achievements has increased rapidly. As an exchange platform and medium for scientific research achievements, scientific and technological academic conferences have become increasingly abundant. The convening of academic conferences brings large numbers of papers, researchers, institutions, projects, and research topics, but massive conference data also makes it difficult for researchers to obtain valuable information efficiently. It is therefore meaningful to use deep learning, knowledge graph technology, semantic similarity calculation, and portrait modeling to mine core information from conference data. This paper reviews the key technologies for constructing knowledge graphs and accurate portraits of scientific and technological academic conferences, including named entity recognition, semantic text similarity, trend prediction, graph storage, search engines, and visualization components. These techniques jointly support the construction of conference knowledge services that help researchers acquire scientific information more quickly.
arXiv:2511.02036v5 Announce Type: replace
Abstract: In real-time Visual SLAM systems, local mapping must operate under strict latency constraints, as delays degrade map quality and increase the risk of tracking failure. GPU parallelization offers a promising way to reduce latency. However, parallelizing local mapping is challenging due to synchronized shared-state updates and the overhead of transferring large map data structures to the GPU. This paper presents TurboMap, a GPU-parallelized and CPU-optimized local mapping backend that holistically addresses these challenges. We restructure Map Point Creation to enable parallel Keypoint Correspondence Search on the GPU, redesign and parallelize Map Point Fusion, optimize Redundant Keyframe Culling on the CPU, and integrate a fast GPU-based Local Bundle Adjustment solver. To minimize data transfer and synchronization costs, we introduce persistent GPU-resident keyframe storage. Experiments on the EuRoC and TUM-VI datasets show average local mapping speedups of 1.3x and 1.6x, respectively, while preserving accuracy.
arXiv:2512.20016v4 Announce Type: replace
Abstract: The Outer Space Treaty (OST) was opened to signatures in 1967, and since then 117 countries, including China, the United States, Russia, have become part of it. Among other stipulations the treaty bans the placement of nuclear weapons in outer space. Recently the US government has raised worries that Russia is testing nuclear-armed anti-satellite weapon components, with the possibility that it will place a nuclear weapon in space. Such a device, if detonated, would destroy most of the satellites in the Low Earth Orbit. This danger is compounded by the lack of a verification mechanism for the OST. No methodologies of verification have been proposed in the open peer reviewed literature. This study presents a concept and a feasibility study for verifying a satellite's compliance to the OST by observing the neutrons induced by spallation from the $\sim$GeV protons in the inner Van Allen radiation belts. The calculations show that a 9U CubeSat sized detection platform can identify a thermonuclear weapon from the distance of 4~km in approximately one week of observation. This conceptual study will stimulate and inform future research and development of verification platforms for OST.
arXiv:2602.06223v2 Announce Type: replace
Abstract: Mobile applications in large-scale distributed systems are susceptible to backend service failures, yet traditional chaos engineering approaches cannot scale mobile testing due to the combinatorial explosion of flows, locations, and failure scenarios that need validation. We present an automated mobile chaos testing system that integrates DragonCrawl, an LLM-based mobile testing platform, with uHavoc, a service-level fault injection system. The key insight is that adaptive AI-driven test execution can navigate mobile applications under degraded backend conditions, eliminating the need to manually write test cases for each combination of user flow, city, and failure type. Since Q1 2024, our system has executed over 180,000 automated chaos tests across 47 critical flows in Uber's Rider, Driver, and Eats applications, representing approximately 39,000 hours of manual testing effort that would be impractical at this scale. We identified 23 resilience risks, with 70% being architectural dependency violations where non-critical service failures degraded core user flows. Twelve issues were severe enough to prevent trip requests or food orders. Two caused application crashes detectable only through mobile chaos testing, not backend testing alone. Automated root cause analysis reduced debugging time from hours to minutes, achieving 88% precision@5 in attributing mobile failures to specific backend services. This paper presents the system design, evaluates its performance under fault injection (maintaining 99% test reliability), and reports operational experience demonstrating that continuous mobile resilience validation is achievable at production scale.
arXiv:2601.02918v3 Announce Type: replace
Abstract: Image Quality Assessment (IQA) is a long-standing problem in computer vision. Previous methods typically focus on predicting numerical scores without explanation or providing low-level descriptions lacking precise scores. Recent reasoning-based vision language models (VLMs) have shown strong potential for IQA by jointly generating quality descriptions and scores. However, existing VLM-based IQA methods often suffer from unreliable reasoning due to their limited capability of integrating visual and textual cues. In this work, we introduce Zoom-IQA, a VLM-based IQA model to explicitly emulate key cognitive behaviors: uncertainty awareness, region reasoning, and iterative refinement. Specifically, we present a two-stage training pipeline: 1) supervised fine-tuning (SFT) on our Grounded-Rationale-IQA (GR-IQA) dataset to teach the model to ground its assessments in key regions, and 2) reinforcement learning (RL) for dynamic policy exploration, stabilized by our KL-Coverage regularizer to prevent reasoning and scoring diversity collapse, with a Progressive Re-sampling Strategy for mitigating annotation bias. Extensive experiments show that Zoom-IQA achieves improved robustness, explainability, and generalization. The application to downstream tasks, such as image restoration, further demonstrates the effectiveness of Zoom-IQA.
arXiv:2602.08417v2 Announce Type: replace
Abstract: Map-based LiDAR pose tracking is essential for long-term autonomous operation, where onboard map priors need be compact for scalable storage and fast retrieval, while online observations are often partial, repetitive, and heavily occluded. We propose Graph-Loc, a graph-based localization framework that tracks the platform pose against compact structural map priors represented as a lightweight point-line graph. Such priors can be constructed from heterogeneous sources commonly available in practice, including polygon outlines vectorized from occupancy/grid maps and CAD/model/floor-plan layouts. For each incoming LiDAR scan, Graph-Loc extracts sparse point and line primitives to form an observation graph, retrieves a pose-conditioned visible subgraph via LiDAR ray simulation, and performs scan-to-map association through unbalanced optimal transport with a local graph-context regularizer. The unbalanced formulation relaxes mass conservation, improving robustness to missing, spurious, and fragmented structures under occlusion. To enhance stability in low-observability segments, we estimate information anisotropy from the refinement normal matrix and defer updates along weakly constrained directions until sufficient constraints reappear. Experiments on public benchmarks, controlled stress tests, and real-world deployments demonstrate accurate and stable tracking with KB-level priors from heterogeneous map sources, including under geometrically degenerate and sustained occlusion and in the presence of gradual scene changes.
arXiv:2602.10746v2 Announce Type: replace
Abstract: With today's mature auto-active program verification tools complex functional requirements can be formalized and proved. To that end, they rely on verification condition generation to bridge between structured programs and high-level specifications and the automated theorem provers used in the background. Integrating software modules into larger systems may necessitate to consider temporal logic requirements, notably liveness properties over infinite traces. Unfortunately, most state-of-the-art tools lack explicit support for such temporal specifications. There are various proposals that address the integration of structured programs and temporal logic, but each comes with some inherent limitation regarding expressiveness or automation. In this paper, we demonstrate a simple but universal solution that can be integrated easily into existing verification condition generators.
arXiv:2602.10844v3 Announce Type: replace
Abstract: In the setting of constructive mathematics, we suggest and study a framework for decidability of properties, which allows for finer distinctions than just "decidable, semidecidable, or undecidable". We work in homotopy type theory and use Brouwer ordinals to specify the level of decidability of a property. In this framework, we express the property that a proposition is $\alpha$-decidable, for a Brouwer ordinal $\alpha$, and show that it generalizes decidability and semidecidability. Further generalizing known results, we show that $\alpha$-decidable propositions are closed under binary conjunction, and discuss for which $\alpha$ they are closed under binary disjunction. We prove that if each $P(i)$ is semidecidable, then the countable meet $\forall i\in \mathbb N. P(i)$ is $\omega^2$-decidable, and similar results for countable joins and iterated quantifiers. We also discuss the relationship with countable choice. All our results are formalized in Cubical Agda.
arXiv:2602.11117v2 Announce Type: replace
Abstract: We present HairWeaver, a diffusion-based pipeline that animates a single human image with realistic and expressive hair dynamics. While existing methods successfully control body pose, they lack specific control over hair, and as a result, fail to capture the intricate hair motions, resulting in stiff and unrealistic animations. HairWeaver overcomes this limitation using two specialized modules: a Motion-Context-LoRA to integrate motion conditions and a Style-Alignment-LoRA to preserve the subject's photoreal appearance across different data domains. These lightweight components are designed to guide a video diffusion backbone while maintaining its core generative capabilities. By training on a specialized dataset of dynamic human motion generated from a CG simulator, HairWeaver affords fine control over hair motion and ultimately learns to produce highly realistic hair that responds naturally to movement. Comprehensive evaluations demonstrate that our approach sets a new state of the art, producing lifelike human hair animations with dynamic details.
arXiv:2603.22916v2 Announce Type: replace
Abstract: In cold-start scenarios, the scarcity of collaborative signals for new items exacerbates the Matthew effect, undermining platform diversity and posing a persistent challenge in practice. Existing methods augment cold-start items' collaborative signals with semantic information, yet face a collaborative-semantic trade-off: collaborative signals work well for popular items but degrade on cold-start ones, while excessive reliance on semantics ignores collaborative differences. To address this, we propose GateSID, which introduces an adaptive gating network to dynamically balance semantic and collaborative signals based on item maturity. We first discretize multimodal features into hierarchical Semantic IDs (SID) via Residual Quantized VAE, then propose two components: (1) Gating-Fused Shared Attention (GFSA), which fuses attention distributions with gate-regulated weights; (2) Gate-Regulated Contrastive Alignment (GRCA), which enforces stronger alignment for cold-start items while relaxing it for popular ones. Experiments on large-scale industrial datasets demonstrate GateSID's superiority over competitive baselines, with the largest gains on popular items. An online A/B test confirms practical effectiveness: GMV +2.6%, CTR +1.1%, and Order +1.6%, with less than 5ms of additional latency. Beyond the method itself, we conduct a comprehensive exploration of SID in ranking models, systematically studying embedding types, SID configurations, and fusion strategies. We hope this exploration offers some useful insights for the community.
arXiv:2605.05969v2 Announce Type: replace
Abstract: GitHub Continuous Integration (CI) workflows increasingly integrate Large Language Models (LLMs) to automate review, triage, content generation, and repository maintenance. This creates a new attack surface: externally controllable workflow inputs can shape LLM prompts and outputs, which may in turn affect security decisions, repository state, or privileged execution. Although LLM security and CI security have each been studied extensively, their intersection remains underexplored. In this paper, we present the first study of LLM-induced security risks in GitHub CI workflows. We characterize the problem along the full execution chain and develop a taxonomy of high-level risk classes and concrete threat vectors. To detect such risks in practice, we design Heimdallr, a hybrid analysis framework that normalizes workflows into an LLM-Workflow Property Graph (L-WPG) and combines triggerability analysis, LLM-assisted dataflow summarization, and deterministic propagation to synthesize concrete threat-vector findings. Evaluated on 300 manually annotated unique workflows, Heimdallr achieves high accuracy on LLM-node identification (F1~=~0.994), triggerability classification (99.8%), and threat-vector detection (micro-average F1~=~0.917). As part of an ongoing detection and disclosure effort, we have so far responsibly disclosed 802 vulnerable workflow instances across 759 repositories and received 71 acknowledgments.
arXiv:2502.12497v2 Announce Type: replace
Abstract: LLMs are rapidly transitioning from research prototypes to core components in production systems across industries such as finance and healthcare. These deployments rely on a growing ecosystem of open-source frameworks and components, collectively forming the LLM supply chain. However, the increasing complexity of this stack introduces critical security risks that remain underexplored. In this work, we present the first systematic and large-scale empirical study of vulnerabilities in the LLM supply chain, analyzing 529 real-world vulnerabilities spanning 77 widely adopted repositories across 12 lifecycle stages. Our findings reveal that the disclosed vulnerabilities are heavily concentrated in the application layer and model integration layer. Among these, 18.5% of the vulnerabilities are LLM-specific, arising from unique architectural and workflow characteristics, such as improper handling of critical resources like model files, prompt templates, and datasets, as well as generative output validation errors. To understand the real-world impact, we examine 63,243 publicly exposed LLM services and find that 45.6% are affected by at least one remotely exploitable vulnerability, over 70% of which are critical or high severity. By correlating these vulnerabilities with their potential exploit scenarios in the wild, we observed that these issues can lead to serious security consequences, including model tampering, sensitive dataset exposure, and unauthorized GPU resource abuse. Based on our findings, we distill 5 actionable insights that can guide engineering teams in auditing and securing LLM services. Our work offers a data-driven foundation for securing the LLM supply chain and highlights urgent directions for both industry and future research.
arXiv:2605.11549v2 Announce Type: replace
Abstract: Reinforcement learning has emerged as a dominant technique for fine-tuning the behavior of large language models, with policy optimization (PO) algorithms such as GRPO, DAPO, and Dr. GRPO emerging in rapid succession to advance state-of-the-art reasoning and alignment performance. However, the modular differences between these algorithms, including targeted improvements to clipping, advantage estimation, and reward aggregation, are introduced across separate papers with inconsistent notation, making them difficult to compare and intimidating to the non-expert community. We present UNIPO, to our knowledge the first interactive visualization tool that exposes the token-level training dynamics of RL fine-tuning algorithms through a unified design. UNIPO connects three complementary views, a high-level training overview, a step-level prompt and response inspector, and a side-by-side algorithm comparison, allowing learners to observe how individual design decisions propagate through training. Through two usage scenarios, we demonstrate how UNIPO supports both classroom instruction for non-experts and algorithm selection for AI practitioners. Our tool is open-source and publicly available at https://poloclub.github.io/unipo.
arXiv:2607.02514v2 Announce Type: replace
Abstract: As AI coding agents become more autonomous, they increasingly ship code iteratively, with the codebase persisting across sessions. This persistence creates a new attack surface: a misaligned or prompt-injected agent can distribute attacks across pull requests (PRs) and time its payload for the PR with the best natural cover. To study the resulting dynamics, we introduce Iterative VibeCoding, a setting for AI control, the study of safely deploying capable but potentially untrusted AI. In Iterative VibeCoding, a coding agent builds software over a sequence of PRs in a persistent codebase while pursuing a covert side task. Our benchmark includes two task families: CLI tools and Flask web services, across 20 total task variations. We use Claude Sonnet 4.5 as the attack agent and GPT-4o as the monitor. We compare gradual attacks, which distribute the side task across PRs, against non-gradual attacks concentrated in a single PR. No single monitor is robust to both: which strategy evades best (success while evading the monitor) depends on the monitor type, so a defender cannot close off both gradual and non-gradual attacks with any one monitor. High evasion (>= 65%) generalizes across model attack agent backends (Sonnet 4.5, Gemini 3.1 Pro, Kimi K2.5), confirming this is a property of the persistent-state attack surface rather than a single model's capability. Evasion also remains high across state-of-the-art monitor models and the gap between gradual and non-gradual evasion widens for more capable models. We introduce a stateful link-tracker monitor that tracks suspicious buildup across PRs. On both task families, it detects gradual attacks substantially better than diff monitors that merely see more accumulated history. Combining this stronger monitor with trajectory monitors in a four-monitor ensemble reduces gradual-attack evasion from 93% under the weakest standard diff monitor to 47%.
arXiv:2502.13828v2 Announce Type: replace
Abstract: Software-defined networking (SDN) separates the control plane from the data plane and exposes the network through software applications and open APIs. The same programmability that drove its adoption also turned the network into a large body of software, and that software can be vulnerable. Knowing where and how SDN software fails is a prerequisite for defending it, yet the literature offers no consolidated account of the problem. We address this gap with a systematic literature review of 113 primary studies published between 2012 and 2025 on the security of the software that makes up SDN. We study how each software component becomes vulnerable, how attackers exploit it, which testing and analysis techniques expose its defects, and how the field has evolved. The review yields a taxonomy of vulnerabilities and attack vectors organized by SDN software component, a synthesis of the methods used to find software defects in each component, and a set of open problems that mark the most promising directions for future work. Earlier surveys treat SDN security as a networking problem; ours is, to our knowledge, the first to treat SDN components as software artifacts whose code, logic, and interactions can be defective. Our artifacts are available at https://github.com/mad975/SDNSoftwareSecurity_SLR.
arXiv:2605.30172v2 Announce Type: replace
Abstract: In this work, we present a compact surrogate circuit for electro-quasi-static (EQS) head modeling. A three-shell geometry (brain, skull, scalp) is considered, and each layer is modeled through radial and tangential pathways, implemented as RC branches. Frequency-dependent tissue conductivity and permittivity are mapped into dispersive resistive and capacitive elements. The model is validated against a semi-analytical spherical-harmonics reference solution over multiple geometrical configurations and operating frequencies, demonstrating good agreement. Neglecting dispersion and capacitive pathways can lead to an overestimation of scalp potentials over the considered frequency range, highlighting the need for dispersive RC circuit modeling.
arXiv:2606.00329v2 Announce Type: replace
Abstract: Recursive systems can enter collapse-like regimes -- self-reinforcing amplification, persistent recursion, and narrowing diversity that mask accelerating internal degradation -- before overt failure becomes visible. We introduce Loopzero, a claim-bounded benchmark framework for testing whether recursive failures follow a directional telemetry pattern: rising gain (G), recursive persistence (p), and declining diversity ($\delta$). The claim boundary is specified in Lean; the Lean artifact does not verify real telemetry, benchmark validity, or detector performance.
We evaluate the bridge on two frozen public-artifact benchmarks: a segmented public-markets benchmark (Volmageddon 2018, COVID MWCB 2020) and a MovieLens-25M offline deterministic recommender replay. Detectors are evaluated under a locked equal-false-positive contract (FP $\in$ [0.03, 0.07], pre-registered) so all configurations face the same alert budget. Neither tested standard comparators nor Loopzero's pre-registered quantile detector achieved an accepted operating point. Directional witness alignment held on both canonical benchmarks, with adjacent-horizon and row-level limitations disclosed. Digitized Shumailov et al. (2024) LLM training-loop trajectories are directionally consistent with the pattern; matched-FP evaluation in that domain is deferred.
The contribution is a reproducible, falsifiable benchmark framework for evaluating recursive-collapse warning claims under an explicit alert-budget contract -- non-acceptance reported as a first-class scientific outcome.
arXiv:2606.01183v5 Announce Type: replace
Abstract: We benchmarked every common open-source FIFO matching-engine implementation we could find, deduplicated, and driven through a single C-ABI harness on one identical workload - 246 distinct engines across more than twenty programming languages. The workload doubles as a byte-identical correctness oracle, and it is unforgiving: only 47 are correct as shipped; it surfaced 267+ distinct defects across the other 199, and we filed 172+ GitHub issues upstream. Our engine leads the 160 that reproduce the consensus by +25 M/s (roughly 4x from the second best) on worst-case throughput, and outruns every engine in the survey written by a professional trading-industry engineer. A single CPU core sustains 33.2~million order messages per second at sub-microsecond median end-to-end host-path latency; a 96-core commodity server (~$1,630/month) sustains ~640 million messages per second across 10,000 symbols - over 20x the provisioned capacity of the U.S. consolidated quote feed.
arXiv:2607.06451v2 Announce Type: replace
Abstract: (shortened for arXiv metadata)
We study the limits of single-server private information retrieval (PIR) with preprocessing. Prior work has shown that single-server PIR with sublinear communication requires a linear number of (public-key) server operations per query [DMO00, DH24]. Recent breakthrough works, including [CHK22, ZPZS24, LMW23], circumvent these lower bounds by critically leveraging preprocessing to construct single-server PIR with sublinear query computation.
Our work presents computation lower bounds for any single-server PIR with preprocessing that makes blackbox usage of {\em any} cryptography (such as random oracles and virtual blackbox obfuscation). For any client preprocessing scheme where the client stores $s$ bits about an $n$-bit database, we prove the online amortized computation must be $\Omega(n/s)$ across $k = \Omega(s)$ queries (even if performed in a single batch query). In more detail, we prove that they must have either $\Omega(n/s)$ amortized online communication or the server must perform $\Omega(n/s)$ cryptographic operations. Our lower bounds are optimal as there exist PIRs with client preprocessing matching exactly one of the above requirements while outperforming the other. Furthermore, our lower bounds also rule out the existence of doubly efficient PIR from blackbox cryptography with sublinear query computation. Our proof framework also supports $\Omega(n/s)$ communication lower bounds for three mildly restricted classes of single-server PIR.
We also prove lower bounds for symmetric private information retrieval (SPIR) with client preprocessing in the random oracle model and present a matching SPIR construction with client preprocessing using only OWFs during queries.
arXiv:2606.21887v2 Announce Type: replace
Abstract: During hot tests on a production line, engine-sound analysis is crucial to ensuring product quality and performance. However, background noise often interferes with accurate sound analysis, leading to potential errors in engine diagnostics. Traditionally, skilled technicians listen to engine sounds to assess engine health, but this is prone to significant inaccuracies. This study presents an innovative deep learning-based approach to address this issue by removing background noise from engine sound recordings using a U-Net neural network structure enhanced with Residual Attention Blocks (RAB-U-Net). Our intelligent noise removal system significantly improves the accuracy of engine noise detection, outperforming traditional techniques and providing a robust solution for real-time applications in production line environments. This study proposes a novel system for engine noise detection in production lines, marking a valuable advancement for the automotive industry in applying deep learning methods to improve the quality of engine diagnostics.