arXiv subjects

Kichang Lee

Publications and source records attributed to Kichang Lee.

15 recordsLinked to original sources

arXiv2026

Auditing Contextual Bias in Human Ball-Strike Calls Using KBO's Automated Umpiring Transition

This paper uses the Korean Baseball Organization's adoption of the Automated Ball-Strike (ABS) system to audit long-standing claims about contextual bias in human ball-strike calls. Using pitch-level KBO data from 2021 through the available portion of the 2026 season, we model called-strike probability for taken pitches near the strike-zone boundary, with 2022-2023 as the primary human-umpire baseline and ABS seasons (2024 and onward) as a diagnostic benchmark. The strongest evidence concerns count pressure. Relative to 0--0 counts, human umpires called substantially fewer strikes in two-strike counts and more strikes in hitter-ahead three-ball counts. Specifically, in the main 0.25-ft boundary band, 0--2 was associated with a -17.17 percentage-point effect and 3--0 with a +6.61 percentage-point effect. Under ABS, the corresponding effects were close to zero and did not survive false-discovery-rate correction. Game progression shows a smaller but coherent pattern as human calls were less strike-prone in early innings and more strike-prone in innings 7--9+, especially in late-close situations, while complete ABS seasons were essentially flat. Other suspected biases are weaker or more localized. Salary-based reputation proxies provide suggestive but proxy-sensitive evidence, and catcher identity shows human-period residual heterogeneity that disappears under ABS. Home-context evidence is mostly null at the umpire level, with one FDR-significant human-period exception and an exploratory umpire-team gap best treated as an audit lead. Overall, the results do not show that human umpires were biased everywhere. Instead, they map where the human strike zone was most context-sensitive, where evidence was weaker, and where common suspicions received little support.

cs.HC↗

arXiv2026

Unified Pitch Graphs for Diagnosing Pitching Strategy

Pitching strategy in baseball is expressed through both physical execution and the ordered context in which pitches are used, yet common representations collapse pitches into discrete types or aggregate statistics. We present Unified Pitch Graphs (UPG), a hierarchical graph representation for retrospective analysis of sequential spatiotemporal events. UPG preserves each pitch as an exact event with reconstructed three-dimensional trajectory and context, connects consecutive pitches through directed sequence edges, and organizes the same events across semantic and temporal resolutions. A support-adaptive mechanism backs off from fine, long sequences when repeated evidence is insufficient, while retaining exact event lineage. We evaluate UPG on 3.94 million MLB Statcast pitches from 2021 to 2026. Nominally identical pitch sequences exhibit distinct physical executions, and ordered structure becomes increasingly evident in longer context-conditioned paths. Support-adaptive backoff increases held-out path coverage from 18.9\% to 94.9\% while improving execution reconstruction from $R^2=0.495$ to $0.685$. UPG also reliably localizes controlled execution changes that discrete pitch-mix and sequence representations cannot detect. These results demonstrate that UPG provides a traceable, multi-scale representation for identifying recurring strategy patterns without conflating retrospective associations with causal or future-performance claims.

cs.IR↗

arXiv2026

Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning

Federated Learning (FL) with Differential Privacy (DP) is increasingly adopted to preserve data confidentiality in distributed machine learning. However, DP noise distorts learned representations and degrades explanation fidelity, limiting differentially private FL where trustworthy explanations are required, such as assistive clinical diagnosis. Prior work adapted DP noise with static feature-importance signals, restricting explainability to post hoc analysis and precluding noise calibration to explanation quality during training. We propose XCal-FL, a closed-loop, explainability-driven local training algorithm for image classification in cross-silo FL that dynamically calibrates DP noise from three complementary signals: (1) prediction logit variations, measuring causal influence on model confidence, (2) counterfactual margins, capturing decision-boundary sensitivity, and (3) saliency concentration, quantifying spatial coherence of model attention, while enforcing formal DP guarantees via adaptive privacy accounting. Experiments on three medical imaging datasets across varying FL configurations show that XCal-FL yields more accurate and interpretable global models, improving predictive performance by over 10\% and explanation fidelity by up to 5$\times$ over static-noise FL, and outperforming state-of-the-art adaptive DP methods in fidelity. XCal-FL also achieves higher privacy-budget efficiency, turning each unit of cumulative privacy loss into larger gains in both accuracy and explanation fidelity. Our analysis further reveals that, unlike predictive performance, which scales roughly linearly with privacy loss, explanation fidelity exhibits non-linear dynamics. These findings suggest explainability is a distinct dimension of the privacy trade-off that cannot be inferred from utility alone, with implications for training and privacy-budget allocation in decision-critical applications.

cs.LG↗

arXiv2026

Temperature Scaling Attack Disrupting Model Confidence in Federated Learning

Predictive confidence serves as a foundational control signal in mission-critical systems, directly governing risk-aware logic such as escalation, abstention, and conservative fallback. While prior federated learning attacks predominantly target accuracy or implant backdoors, we identify confidence calibration as a distinct attack objective. We present the Temperature Scaling Attack (TSA), a training-time attack that degrades calibration while preserving accuracy. By injecting temperature scaling with learning rate-temperature coupling during local training, TSA shifts model confidence while keeping predictive accuracy and common optimization signals close to benign training. We provide a convergence analysis under non-IID settings, showing that the coupling controls the primary update scale while leaving a bounded temperature-induced residual, yielding the standard non-convex FL convergence structure with an additional residual term. Across three benchmarks, TSA substantially shifts calibration (e.g., 145% error increase on CIFAR-100) with <2% accuracy change, and remains effective under robust aggregation and post-hoc calibration defenses. Case studies further show up to a 7.2x increase in missed verifications in healthcare and severe confidence-gating failures in autonomous driving, even when accuracy is unchanged. Overall, our results establish calibration integrity as a critical attack surface in federated learning.

cs.LG↗

arXiv2025

Spatial Discretization for Fine-Grain Zone Checks with STARKs

Many location-based services rely on a point-in-polygon test (PiP), checking whether a point or a trajectory lies inside a geographic zone. Since geometric operations are expensive in zero-knowledge proofs, privately performing the PiP test is challenging. In this paper, we answer the research questions of how different ways of encoding zones affect accuracy and proof cost by exploiting gridbased lookup tables under a fixed STARK execution model. Beyond a Boolean grid-based baseline that marks cells as in- or outside, we explore a distance-aware encoding approach that stores how far each cell is from a zone boundary and uses interpolation to reason within a cell. Our experiments on real-world data demonstrate that the proposed distance-aware approach achieves higher accuracy on coarse grids (max. 60%p accuracy gain) with only a moderate verification overhead (approximately 1.4x), making zone encoding the key lever for efficient zero-knowledge spatial checks.

cs.CR↗

arXiv2025

Now or Never: Continuous Surveillance AIoT System for Ephemeral Events in Intermittent Sensor Networks

Wilderness monitoring tasks, such as poaching surveillance and forest fire detection, require pervasive and high-accuracy sensing. While AIoT offers a promising path, covering vast, inaccessible regions necessitates the massive deployment of maintenance-free, battery-less nodes with limited computational resources. However, these constraints create a critical `Availability Gap.' Conventional intermittent operations prioritize computation throughput, forcing sensors to sleep during energy buffering. Consequently, systems miss ephemeral, `now-or-never' events (e.g., Vocalizations of natural monuments or Fire), which is fatal for detecting rare but high-stakes anomalies. To address this, we propose an Energy-aware Elastic Split Computing Algorithm that prioritizes continuous sensing by dynamically offloading tasks to energy-rich neighbors. Preliminary results demonstrate stable monitoring of an additional $2,496\;\text{m}^2$ and the capture of approximately 103 more critical events per day. Ultimately, this algorithm establishes a robust foundation for building resilient, fail-safe surveillance systems even on resource-constrained nodes.

eess.SY↗

arXiv2025

Verifiable Dropout: Turning Randomness into a Verifiable Claim

Modern cloud-based AI training relies on extensive telemetry and logs to ensure accountability. While these audit trails enable retrospective inspection, they struggle to address the inherent non-determinism of deep learning. Stochastic operations, such as dropout, create an ambiguity surface where attackers can mask malicious manipulations as natural random variance, granting them plausible deniability. Consequently, existing logging mechanisms cannot verify whether stochastic values were generated and applied honestly without exposing sensitive training data. To close this integrity gap, we introduce Verifiable Dropout, a privacy-preserving mechanism based on zero-knowledge proofs. We treat stochasticity not as an excuse but as a verifiable claim. Our approach binds dropout masks to a deterministic, cryptographically verifiable seed and proves the correct execution of the dropout operation. This design enables users to audit the integrity of stochastic training steps post-hoc, ensuring that randomness was neither biased nor cherry-picked, while strictly preserving the confidentiality of the model and data.

cs.CR↗

arXiv2025

Exploring Large Language Model as an Interactive Sports Coach: Lessons from a Single-Subject Half Marathon Preparation

Large language models (LLMs) are emerging as everyday assistants, but their role as longitudinal virtual coaches is underexplored. This two-month single subject case study documents LLM guided half marathon preparation (July-September 2025). Using text based interactions and consumer app logs, the LLM acted as planner, explainer, and occasional motivator. Performance improved from sustaining 2 km at 7min 54sec per km to completing 21.1 km at 6min 30sec per km, with gains in cadence, pace HR coupling, and efficiency index trends. While causal attribution is limited without a control, outcomes demonstrate safe, measurable progress. At the same time, gaps were evident, no realtime sensor integration, text only feedback, motivation support that was user initiated, and limited personalization or safety guardrails. We propose design requirements for next generation systems, persistent athlete models with explicit guardrails, multimodal on device sensing, audio, haptic, visual feedback, proactive motivation scaffolds, and privacy-preserving personalization. This study offers grounded evidence and a design agenda for evolving LLMs from retrospective advisors to closed-loop coaching companions.

cs.HC↗

arXiv2025

FedUNet: A Lightweight Additive U-Net Module for Federated Learning with Heterogeneous Models

Federated learning (FL) enables decentralized model training without sharing local data. However, most existing methods assume identical model architectures across clients, limiting their applicability in heterogeneous real-world environments. To address this, we propose FedUNet, a lightweight and architecture-agnostic FL framework that attaches a U-Net-inspired additive module to each client's backbone. By sharing only the compact bottleneck of the U-Net, FedUNet enables efficient knowledge transfer without structural alignment. The encoder-decoder design and skip connections in the U-Net help capture both low-level and high-level features, facilitating the extraction of clientinvariant representations. This enables cooperative learning between the backbone and the additive module with minimal communication cost. Experiment with VGG variants shows that FedUNet achieves 93.11% accuracy and 92.68% in compact form (i.e., a lightweight version of FedUNet) with only 0.89 MB low communication overhead.

cs.LG↗

arXiv2025

Toward Storage-Aware Learning with Compressed Data An Empirical Exploratory Study on JPEG

On-device machine learning is often constrained by limited storage, particularly in continuous data collection scenarios. This paper presents an empirical study on storage-aware learning, focusing on the trade-off between data quantity and quality via compression. We demonstrate that naive strategies, such as uniform data dropping or one-size-fits-all compression, are suboptimal. Our findings further reveal that data samples exhibit varying sensitivities to compression, supporting the feasibility of a sample-wise adaptive compression strategy. These insights provide a foundation for developing a new class of storage-aware learning systems. The primary contribution of this work is the systematic characterization of this under-explored challenge, offering valuable insights that advance the understanding of storage-aware learning.

cs.LG↗

arXiv2024

Tazza: Shuffling Neural Network Parameters for Secure and Private Federated Learning

Federated learning enables decentralized model training without sharing raw data, preserving data privacy. However, its vulnerability towards critical security threats, such as gradient inversion and model poisoning by malicious clients, remain unresolved. Existing solutions often address these issues separately, sacrificing either system robustness or model accuracy. This work introduces Tazza, a secure and efficient federated learning framework that simultaneously addresses both challenges. By leveraging the permutation equivariance and invariance properties of neural networks via weight shuffling and shuffled model validation, Tazza enhances resilience against diverse poisoning attacks, while ensuring data confidentiality and high model accuracy. Comprehensive evaluations on various datasets and embedded platforms show that Tazza achieves robust defense with up to 6.7x improved computational efficiency compared to alternative schemes, without compromising performance.

cs.LG↗

arXiv2024

DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning

Federated Learning (FL) enables collaborative model training across distributed devices while preserving local data privacy, making it ideal for mobile and embedded systems. However, the decentralized nature of FL also opens vulnerabilities to model poisoning attacks, particularly backdoor attacks, where adversaries implant trigger patterns to manipulate model predictions. In this paper, we propose DeTrigger, a scalable and efficient backdoor-robust federated learning framework that leverages insights from adversarial attack methodologies. By employing gradient analysis with temperature scaling, DeTrigger detects and isolates backdoor triggers, allowing for precise model weight pruning of backdoor activations without sacrificing benign model knowledge. Extensive evaluations across four widely used datasets demonstrate that DeTrigger achieves up to 251x faster detection than traditional methods and mitigates backdoor attacks by up to 98.9%, with minimal impact on global model accuracy. Our findings establish DeTrigger as a robust and scalable solution to protect federated learning environments against sophisticated backdoor threats.

cs.LG↗

arXiv2024

Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generation

While federated learning leverages distributed client resources, it faces challenges due to heterogeneous client capabilities. This necessitates allocating models suited to clients' resources and careful parameter aggregation to accommodate this heterogeneity. We propose HypeMeFed, a novel federated learning framework for supporting client heterogeneity by combining a multi-exit network architecture with hypernetwork-based model weight generation. This approach aligns the feature spaces of heterogeneous model layers and resolves per-layer information disparity during weight aggregation. To practically realize HypeMeFed, we also propose a low-rank factorization approach to minimize computation and memory overhead associated with hypernetworks. Our evaluations on a real-world heterogeneous device testbed indicate that \system enhances accuracy by 5.12% over FedAvg, reduces the hypernetwork memory requirements by 98.22%, and accelerates its operations by 1.86x compared to a naive hypernetwork approach. These results demonstrate HypeMeFed's effectiveness in leveraging and engaging heterogeneous clients for federated learning.

cs.LG↗

arXiv2024

Analyzing the Impact of the Automatic Ball Strike System in Professional Baseball through a Case Study on KBO League Data

Recent advancements in professional baseball have led to the introduction of the Automated Ball-Strike (ABS) system, or ``robot umpires,'' which utilize machine learning, computer vision, and precise tracking technologies to automate ball-strike calls. The Korean Baseball Organization (KBO) league became the first professional baseball league to implement ABS during the 2024 season. Leveraging pitch data from 2,515 KBO games across multiple seasons and employing mathematical modeling, we examine the aggregate decision tendencies of human umpires versus those of the ABS within the ``gray zone'' of the strike zone. We propose and answer four research questions to examine the differences between human and robot umpires, player adaptation to ABS, assess the ABS system's fairness and consistency, and analyze its strategic implications for the game. Our findings offer valuable insights into the impact of technological integration in sports officiating, providing lessons relevant to future implementations in professional baseball and beyond.

cs.HC↗

arXiv2024

Improving Local Training in Federated Learning via Temperature Scaling

Federated learning is inherently hampered by data heterogeneity: non-i.i.d. training data over local clients. We propose a novel model training approach for federated learning, FLex&Chill, which exploits the Logit Chilling method. Through extensive evaluations, we demonstrate that, in the presence of non-i.i.d. data characteristics inherent in federated learning systems, this approach can expedite model convergence and improve inference accuracy. Quantitatively, from our experiments, we observe up to 6X improvement in the global federated learning model convergence time, and up to 3.37% improvement in inference accuracy.

cs.LG↗