arXiv subjects

Hanlin Cai

Publications and source records attributed to Hanlin Cai.

18 recordsLinked to original sources

arXiv2026

Deadline-Bound Finite-Object Delivery over Intermittent LEO Satellite Contact Plans under Residual-Service Accounting

Low-Earth-orbit (LEO) relay networks deliver finite objects -- sensing tiles, telemetry blocks, model updates, and checkpoints -- over intermittent inter-satellite and space-to-ground contact plans. Partial delivery is insufficient when the complete object misses its deadline. When an object is split across candidate paths, a path-private evaluation can count the same contact service more than once and silently under-count completion. We develop a residual-service-aware delivery layer that consumes candidate paths from contact-plan route generation and tests whether the complete object can be delivered before its deadline under per-edge first-in-first-out residual service. Under controlled shared-contact contention, path-private evaluation under-counts completion by up to 154 s and can report finite completion for a fixed plan with no residual-service completion. For edge-disjoint complementary contacts, the layer reduces to fixed-path service; we derive a sufficient service-budget condition under which two-way striping strictly enlarges the feasible payload region. We verify a restricted exhaustive reference, characterize runtime over a 20-180-satellite procedural contact model, and show that bounded two-way striping reduces mean and median gaps to the restricted reference by about 40%, while P90 and worst-case gaps remain unchanged.

eess.SP↗

arXiv2026

A reversed solar illumination dependence of unintended emission from Starlink Direct-to-Cell satellites at 72-234 MHz with the EDA2

Second-generation Starlink Direct-to-Cell (DTC) satellites carry an additional payload for direct cellular phone connectivity whose unintended electromagnetic radiation (UEMR) at sub-300 MHz frequencies has not been individually characterised. We reanalyse 112,534 detections from 1,806 Starlink satellites observed with the Engineering Development Array version 2 (EDA2) at 21 frequencies between 72.685 and 234.375 MHz (Grigg et al. 2025), separating 175 DTC and 1,623 Ku-only v2-Mini comparison satellites via the McDowell General Catalogue (McDowell 2020). DTC satellites emit a range-corrected flux density 1.45x that of the Ku-only comparison (Cliff's delta = +0.30, p = 2.6e-11). At 230.469 MHz the XX detection fraction reaches 0.811 against a 0.481 baseline (p ~ 1e-274), and 11 of 21 frequency channels show Benjamini-Hochberg-significant polarisation anomalies. The DTC population is brighter in eclipse than in sunlight (illuminated/eclipsed flux density ratio 0.47) while the Ku-only comparison shows the opposite sense (1.18); the reversal persists across altitude, sub-satellite latitude, frequency, and launch-epoch matching. The reversal strongly disfavours UEMR mechanisms that scale monotonically with instantaneous solar photocurrent and favours an active on-board source whose effective duty cycle is larger at lower equilibrium temperature. Within the 230.469 MHz coarse channel, fine-channel inspection isolates the excess to a single ~24 kHz bin near 230.627 MHz, tail-driven and absent at five control channels. Three falsifiable mechanism-discrimination tests show this feature is not coincident with the LOFAR-resolved Bassa et al. (2024) clock fundamentals, is unresolved at the EDA2 24 kHz resolution, and is heterogeneously expressed across the v2-Mini fleet rather than driven by a few permanently bright units or by uniform thermal scaling.

eess.SP↗

arXiv2026

Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs

Federated fine-tuning (FFT) has emerged as a privacy-preserving paradigm for collaboratively adapting large language models (LLMs). Built upon federated learning, FFT enables distributed agents to jointly refine a shared pretrained LLM by aggregating local LLM updates without sharing local raw data. However, FFT-based LLMs remain vulnerable to model manipulation threats, in which adversarial participants upload manipulated LLM updates that corrupt the aggregation process and degrade the performance of the global LLM. In this paper, we propose an Augmented Model maniPulation (AugMP) strategy against FFT-based LLMs. Specifically, we design a novel graph representation learning framework that captures feature correlations among benign LLM updates to guide the generation of malicious updates. To enhance manipulation effectiveness and stealthiness, we develop an iterative manipulation algorithm based on an augmented Lagrangian dual formulation. Through this formulation, malicious updates are optimized to embed adversarial objectives while preserving benign-like parameter characteristics. Experimental results across multiple LLM backbones demonstrate that the AugMP strategy achieves the strongest manipulation performance among all competing baselines, reducing the global LLM accuracy by up to $26\%$ and degrading the average accuracy of local LLM agents by up to $22\%$. Meanwhile, AugMP maintains high statistical and geometric consistency with benign updates, enabling it to evade conventional distance- and similarity-based defense methods.

cs.LG↗

arXiv2026

Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification

Adversarial attacks pose a severe threat to the reliability of deep learning models in remote sensing (RS) image classification. Most existing methods rely on direct pixel-wise perturbations, failing to exploit the inherent atmospheric characteristics of RS imagery or survive real-world image degradations. In this paper, we propose FogFool, a physically plausible adversarial framework that generates fog-based perturbations by iteratively optimizing atmospheric patterns based on Perlin noise. By modeling fog formations with natural, irregular structures, FogFool generates adversarial examples that are not only visually consistent with authentic RS scenes but also deceptive. By leveraging the spatial coherence and mid-to-low-frequency nature of atmospheric phenomena, FogFool embeds adversarial information into structural features shared across diverse architectures. Extensive experiments on two benchmark RS datasets demonstrate that FogFool achieves superior performance: not only does it exceed in white-box settings, but also exhibits exceptional black-box transferability (reaching 83.74% TASR) and robustness against common preprocessing-based defenses such as JPEG compression and filtering. Detailed analyses, including confusion matrices and Class Activation Map (CAM) visualizations, reveal that our atmospheric-driven perturbations induce a universal shift in model attention. These results indicate that FogFool represents a practical, stealthy, and highly persistent threat to RS classification systems, providing a robust benchmark for evaluating model reliability in complex environments.

cs.CV↗

arXiv2026

Rain Rate Estimation Bounds and Weather-Adaptive Pilot Allocation for LEO Satellite ISAC

Rain attenuates Ku-band satellite signals by up to 20~dB, encoding precipitation information along the Earth-space slant path. This paper derives the Bayesian Cram\'{e}r-Rao bound (BCRB) for rain rate estimation from LEO broadband OFDM downlinks. Using corrected ITU-R P.838-3 coefficients, the standard CRB yields a minimum detectable rain rate $R_{\min} \approx 4.3\mmh$ for a single link at the $38^\circ$ reference elevation. We derive the prior Fisher information in closed form for log-normal rain ($c_v = 1.05$, from 186{,}292 samples) and show that a single-snapshot BCRB reduces $R_{\min}$ to $1.1\mmh$; exploiting temporal correlation ($\rho = 0.95$) over a 30-min window further tightens it to $0.95\mmh$, while multi-link fusion across $N = 215$ links lowers the operating-point RMSE \emph{lower bound} at $R = 20\mmh$ to approximately $0.07\mmh$. Building on these bounds, we formulate a weather-adaptive pilot allocation that minimizes the BCRB subject to a hard spectral-efficiency constraint, characterize its three-regime structure (full-sensing, throughput-tracking, outage), and pair it with a CUSUM rain onset detector achieving sub-10-min delay for $R \geq 20\mmh$. A closed-form analysis of dynamic LEO slant geometry identifies a sensing-optimal elevation at the P.618-validity floor of $15^\circ$ that yields a $1.58\times$ geometric improvement over the $38^\circ$ baseline, exposing a structural anti-correlation between sensing- and communication-optimal elevations along an orbital pass. Validation against 9.4~million radar samples from 215 Ku-band GEO satellite links ($r = 0.72$, RMSE~$= 1.24\dB$) and 113 rain gauges confirms the underlying attenuation model; the bounds transfer to LEO constellations under matched OFDM signal parameters, with dedicated LEO validation left for future work.

eess.SP↗

arXiv2026

Performance Bounds and Robust Filtering for LEO Inter-Satellite Synchronization under Cross-Epoch Doppler Coupling

Low Earth orbit (LEO) inter-satellite links (ISLs) must achieve joint synchronization and ranging under severe hardware impairments, namely oscillator phase noise, clock drift, and measurement outliers, exacerbated by rapid relative dynamics exceeding 7~km/s. In coherent Doppler processing, the frequency observable depends on the \emph{difference} between consecutive carrier phase states, creating a cross-epoch coupling structure that fundamentally affects estimation-theoretic performance limits. This paper makes three contributions. First, we prove analytically that this cross-epoch Doppler coupling is \emph{necessary} to avoid unbounded carrier phase uncertainty: without it, phase variance grows linearly without bound. Second, we derive a posterior Cram\'{e}r-Rao bound (PCRB) via the Tichavsk\'{y} recursion that explicitly incorporates the resulting 10$\times$10 block information structure. Third, we propose a hybrid robust filtering framework combining hard gating for impulsive cycle-slip outliers with Huber M-estimation for heavy-tail contamination, using TASD-aware innovation covariance to account for cross-epoch uncertainty in residual normalization. Monte Carlo simulations at Ka-band confirm that the PCRB accurately lower-bounds estimator performance under nominal conditions, while the hybrid method reduces 95th-percentile phase error by 27--93\% compared to standard extended Kalman filtering across different outlier regimes.

eess.SP↗

arXiv2026

Edge-Side Fingerprints of Service Tiering and Quota Throttling in Starlink

We design and evaluate an edge-side measurement procedure for auditing service tiering and quota-based throttling in Starlink. Using a 232.8-hour plan-hopping campaign on a UK residential terminal, we align 1 Hz terminal telemetry with host-side probes to obtain portal-labeled traces spanning priority, post-quota throttling, stay-active operation, and residential service. These regimes manifest as distinct signatures in goodput, PoP RTT, and an internal-to-user ratio $R=C_{\mathrm{int}}/T_{\mathrm{user}}$. We further show that high-speed $R$ is stable over 30-minute sub-windows, that low-rate clusters have no aligned persistent obstruction or PoP-loss signature, and that clean high-speed dips do not move $R$ into the low-rate band. A lightweight rule on windowed medians separates high-speed from low-rate operation on this trace without operator visibility.

eess.SP↗

arXiv2025

A $p$-adic Simpson correspondence for singular rigid-analytic varieties

Let $C$ be a complete, algebraically closed non-archimedean extension of $\mathbb{Q}_p$, and $X$ be a proper rigid-analytic variety over $C$. We show that the category of pro-\'etale vector bundles on $X$ is equivalent to the category of Higgs bundles on the $\eh$-site of $X$, thereby generalizing the work of Faltings and Heuer to arbitrary proper rigid-analytic varieties.

math.AG↗

arXiv2025

Environment-to-Link ISAC with Space-Weather Sensing for Ka-Band LEO Downlinks

Ka-band low-Earth-orbit (LEO) downlinks can suffer second-scale reliability collapses during flare-driven ionospheric disturbances, where fixed fade margins and reactive adaptive coding and modulation (ACM) are either overly conservative or too slow. This paper presents a GNSS-free, link-internal predictive controller that senses the same downlink via a geometry-free dual-carrier phase observable at 10~Hz: a high-pass filter and template-based onset detector, followed by a four-state nearly-constant-velocity Kalman filter, estimate $\Delta$VTEC and its rate, and a short look-ahead (60~s) yields an endpoint outage probability used as a risk gate to trigger one-step discrete MCS down-switch and pilot-time update with hysteresis. Evaluation uses physics-informed log replay driven by real GOES X-ray flare morphologies under a disjoint-day frozen-calibration protocol, with uncertainty reported via paired moving-block bootstrap. Across stressed 60~s windows, the controller reduces peak BLER by 25--30\% and increases goodput by 0.10--0.15~bps/Hz versus no-adaptation baselines under a unified link-level abstraction. The loop runs in $\mathcal{O}(1)$ per 0.1~s epoch (about 0.042~ms measured), making on-board implementation feasible, and scope and deployment considerations for dispersion-dominated events are discussed.

eess.SP↗

arXiv2025

Graph Representation-based Model Poisoning on the Heterogeneous Internet of Agents

Internet of Agents (IoA) envisions a unified, agent-centric paradigm where heterogeneous large language model (LLM) agents can interconnect and collaborate at scale. Within this paradigm, federated fine-tuning (FFT) serves as a key enabler that allows distributed LLM agents to co-train an intelligent global LLM without centralizing local datasets. However, the FFT-enabled IoA systems remain vulnerable to model poisoning attacks, where adversaries can upload malicious updates to the server to degrade the performance of the aggregated global LLM. This paper proposes a graph representation-based model poisoning (GRMP) attack, which exploits overheard benign updates to construct a feature correlation graph and employs a variational graph autoencoder to capture structural dependencies and generate malicious updates. A novel attack algorithm is developed based on augmented Lagrangian and subgradient descent methods to optimize malicious updates that preserve benign-like statistics while embedding adversarial objectives. Experimental results show that the proposed GRMP attack can substantially decrease accuracy across different LLM models while remaining statistically consistent with benign updates, thereby evading detection by existing defense mechanisms and underscoring a severe threat to the ambitious IoA paradigm.

cs.NI↗

arXiv2025

Fundamental Limits of Cooperative Integrated Sensing and Communications over Low-Earth Orbit THz Satellite Channels

Terahertz inter-satellite links enable unprecedented sensing precision for Low Earth Orbit (LEO) constellations, yet face fundamental bounds from hardware impairments, pointing errors, and network interference. We develop a Network Cram\'er-Rao Lower Bound (N-CRLB) framework incorporating dynamic topology, hardware quality factor $\Gamma_{\text{eff}}$, phase noise $\sigma^2_\phi$, and cooperative effects through recursive Fisher Information analysis. Our analysis reveals three key insights: (i) hardware and phase noise create power-independent performance ceilings ($\sigma_{\text{ceiling}} \propto \sqrt{\Gamma_{\text{eff}}}$) and floors ($\sigma_{\text{floor}} \propto \sqrt{\sigma^2_\phi}/f_c$), with power-only scaling saturating above $\text{SNR}_{\text{crit}}=1/\Gamma_{\text{eff}}$; (ii) interference coefficients $\alpha_{\ell m}$ enable opportunistic sensing with demonstrated gains of 5.5~dB under specific conditions (65~dB processing gain, 50~dBi antennas); (iii) measurement correlations from shared timing references, when properly modeled, do not degrade performance and can provide common-mode rejection benefits compared to mismodeled independent-noise baselines. Sub-millimeter ranging requires co-optimized hardware ($\Gamma_{\text{eff}}<0.01$), oscillators ($\sigma^2_\phi<10^{-2}$), and appropriate 3D geometry configurations.

eess.SP↗

arXiv2025

Graph Representation-based Model Poisoning on Federated Large Language Models

Federated large language models (FedLLMs) enable powerful generative capabilities within wireless networks while preserving data privacy. Nonetheless, FedLLMs remain vulnerable to model poisoning attacks. This article first reviews recent advancements in model poisoning techniques and existing defense mechanisms for FedLLMs, underscoring critical limitations, especially when dealing with non-IID textual data distributions. Current defense strategies predominantly employ distance or similarity-based outlier detection mechanisms, relying on the assumption that malicious updates markedly differ from benign statistical patterns. However, this assumption becomes inadequate against adaptive adversaries targeting billion-parameter LLMs. The article further investigates graph representation-based model poisoning (GRMP), an emerging attack paradigm that exploits higher-order correlations among benign client gradients to craft malicious updates indistinguishable from legitimate ones. GRMP can effectively circumvent advanced defense systems, causing substantial degradation in model accuracy and overall performance. Moreover, the article outlines a forward-looking research roadmap that emphasizes the necessity of graph-aware secure aggregation methods, specialized vulnerability metrics tailored for FedLLMs, and evaluation frameworks to enhance the robustness of federated language model deployments.

cs.CR↗

arXiv2025

Applying LLM-Powered Virtual Humans to Child Interviews in Child-Centered Design

In child-centered design, directly engaging children is crucial for deeply understanding their experiences. However, current research often prioritizes adult perspectives, as interviewing children involves unique challenges such as environmental sensitivities and the need for trust-building. AI-powered virtual humans (VHs) offer a promising approach to facilitate engaging and multimodal interactions with children. This study establishes key design guidelines for LLM-powered virtual humans tailored to child interviews, standardizing multimodal elements including color schemes, voice characteristics, facial features, expressions, head movements, and gestures. Using ChatGPT-based prompt engineering, we developed three distinct Human-AI workflows (LLM-Auto, LLM-Interview, and LLM-Analyze) and conducted a user study involving 15 children aged 6 to 12. The results indicated that the LLM-Analyze workflow outperformed the others by eliciting longer responses, achieving higher user experience ratings, and promoting more effective child engagement.

cs.HC↗

arXiv2025

Semantic Communication for the Internet of Space: New Architecture, Challenges, and Future Vision

The expansion of sixth-generation (6G) wireless networks into space introduces technical challenges that conventional bit-oriented communication approaches cannot efficiently address, including intermittent connectivity, severe latency, limited bandwidth, and constrained onboard resources. To overcome these limitations, semantic communication has emerged as a transformative paradigm, shifting the communication focus from transmitting raw data to delivering context-aware, missionrelevant information. In this article, we propose a semantic communication architecture explicitly tailored for the 6G Internet of Space (IoS), integrating multi-modal semantic processing, AIdriven semantic encoding and decoding, and adaptive transmission mechanisms optimized for space environments. The effectiveness of our proposed framework is demonstrated through a representative deep-space scenario involving semantic-based monitoring of Mars dust storms. Finally, we outline open research challenges and discuss future directions toward realizing practical semantic-enabled IoS systems.

cs.NI↗

arXiv2025

Semantic Learning for Molecular Communication in Internet of Bio-Nano Things

Molecular communication (MC) provides a foundational framework for information transmission in the Internet of Bio-Nano Things (IoBNT), where efficiency and reliability are crucial. However, the inherent limitations of molecular channels, such as low transmission rates, noise, and intersymbol interference (ISI), limit their ability to support complex data transmission. This paper proposes an end-to-end semantic learning framework designed to optimize task-oriented molecular communication, with a focus on biomedical diagnostic tasks under resource-constrained conditions. The proposed framework employs a deep encoder-decoder architecture to efficiently extract, quantize, and decode semantic features, prioritizing taskrelevant semantic information to enhance diagnostic classification performance. Additionally, a probabilistic channel network is introduced to approximate molecular propagation dynamics, enabling gradient-based optimization for end-to-end learning. Experimental results demonstrate that the proposed semantic framework improves diagnostic accuracy by at least 25% compared to conventional JPEG compression with LDPC coding methods under resource-constrained communication scenarios.

eess.SP↗

arXiv2025

Plus-pure thresholds of some cusp-like singularities in mixed characteristic

Log-canonical and $F$-pure thresholds of pairs in equal characteristic admit an analog in the recent theory of singularities in mixed characteristic, which is known as the plus-pure threshold. In this paper we study plus-pure thresholds for singularities of the form $p^a + x^b \in {\bf Z}_p [[ x ]]$, showing that in a number of cases this plus-pure threshold agrees with the $F$-pure threshold of the singularity $t^a + x^b \in {\bf F}_p [[ t, x ]]$. We also discuss a few other sporadic examples.

math.AG↗

arXiv2025

Characterizing perfectoid covers of abelian varieties

We give a simple characterization of all perfectoid profinite \'{e}tale covers of abelian varieties in terms of the Hodge-Tate filtration on the $p$-adic Tate module. We also compute the geometric Sen morphism for all profinite $p$-adic Lie torsors over an abelian variety, and combine this with our characterization to prove a conjecture of Rodr\'{i}guez Camargo on perfectoidness of $p$-adic Lie torsors in this case. We obtain complementary results for covers of semi-abeloid varieties, $p$-divisible rigid analytic groups, and varieties with globally generated 1-forms. Our proof of perfectoidness for covers of abelian varieties is based on results of Scholze on the canonical subgroup and holds for an arbitrary abelian variety over an algebraically closed non-archimedean extension of $\mathbb{Q}_p$. In an appendix authored by Tongmu He, an alternate proof is presented in the case of abelian varieties that can be defined over a discretely valued subfield by combining our computation of the geometric Sen morphism with previous pointwise perfectoidness and purity of perfectoidness results of He.

math.NT↗

arXiv2022

Perfectoid signature, perfectoid Hilbert-Kunz multiplicity, and an application to local fundamental groups

We define a (perfectoid) mixed characteristic version of $F$-signature and Hilbert-Kunz multiplicity by utilizing the perfectoidization functor of Bhatt-Scholze and Faltings' normalized length (also developed in the work of Gabber-Ramero). We show that these definitions coincide with the classical theory in equal characteristic $p > 0$. We prove that a ring is regular if and only if either its perfectoid signature or perfectoid Hilbert-Kunz multiplicity is 1 and we show that perfectoid Hilbert-Kunz multiplicity characterizes BCM closure and extended plus closure of $m$-primary ideals. We demonstrate that perfectoid signature detects BCM-regularity and transforms similarly to $F$-signature or normalized volume under quasi-\'etale maps. As a consequence, we prove that BCM-regular rings have finite local \'etale fundamental group and also finite torsion part of their divisor class groups. Finally, we also define a mixed characteristic version of relative rational signature, and show it characterizes BCM-rational singularities.

math.AC↗