Defense Notices

Graph Neural Networks (GNNs) achieve state-of-the-art performance in modeling complex biological and behavioral systems, yet their "black-box" nature limits their utility for scientific discovery and clinical translation. Standard post-hoc explainability methods typically attribute importance to low-level features, such as individual nodes or edges, which often fail to map onto the high-level, domain-specific concepts utilized by experts. To address this gap, this thesis explores diverse methodological strategies for achieving Concept-Level Interpretability in GNNs, demonstrating how deep learning models can be structurally and analytically aligned with expert domain knowledge. This theme is explored through two distinct methodological paradigms applied to critical challenges in neuroscience and clinical psychology. First, we introduce an interpretable-by-design approach for modeling brain structure-function coupling. By employing an ensemble of GNNs conceptually biased via input graph filtering, the model enforces verifiably disentangled node embeddings. This allows for the quantitative testing of specific structural hypotheses, revealing that a minority of strong anatomical connections disproportionately drives functional connectivity predictions. Second, we present a post-hoc conceptual alignment paradigm for quantifying atypical motor signatures in Autism Spectrum Disorder (ASD). Utilizing a Spatio-Temporal Graph Autoencoder (STGCN-AE) trained on normative skeletal data, we establish an unsupervised anomaly detection system. To provide clinical interpretability, the model's reconstruction error is systematically aligned with a library of human-interpretable kinematic features, such as postural sway and limb jerk. Explanatory meta-modeling via XGBoost and SHAP analysis further translates this abstract loss into a multidimensional clinical signature. Together, these applications demonstrate that integrating concept-level interpretability through either architectural design or systematic post-hoc alignment enables GNNs to serve as robust tools for hypothesis testing and clinical assessment.

Non-coding RNAs fold into complex 3D structures that govern their biological functions, with RNA structural motifs (RSMs) serving as conserved building blocks of this architecture.
These motifs are defined by characteristic base-interaction patterns, making accurate identification and classification of RNA interactions essential for understanding RNA structure and function.

Despite their biological importance, accurately identifying and classifying these interactions remains challenging because the available data are highly variable in quality and scarce in quantity. This compromises annotation reliability, hinders the construction of trustworthy ground truth for systematic assessment, and restricts the supply of reliable training examples needed for supervised learning.

To address this, we introduce NoBIAS, the first resolution-aware, integrated machine learning-based suite for annotating base interactions from 3D RNA structures, inspired by human pattern recognition, augmented with structure prediction for data enrichment, and evaluated on a carefully curated, stratified benchmark.

NoBIAS is a hierarchical framework for RNA base-interaction annotation that integrates interaction-specific inductive biases with multimodal representation learning. By combining a convolution-augmented, rule-guided module for stacking interactions with complementary graph and image encoders for pairing interactions, NoBIAS captures both structural priors and local visual cues of RNA base doublets. A performance-calibrated logit fusion scheme then adaptively integrates modality-specific predictions based on local-structural resolution, enabling robust inference across heterogeneous 3D RNA structures.

Evaluation across multiple benchmark tiers: spanning consensus, homolog-supported, and manually verified cases, shows that NoBIAS consistently outperforms existing methods under increasingly challenging conditions. Together, the NoBIAS design and its evaluation framework provide a systematic foundation for robust RNA base-interaction annotation, enabling more reliable analysis of RNA structure under realistic uncertainty.

Secure and scalable authentication has become a primary requirement in modern digital ecosystems, where both human biometrics and electronic identities must be verified under noise, large population growth and resource constraints. Existing approaches often struggle to simultaneously provide storage efficiency, dynamic updates and strong authentication reliability. The proposed work advances a unified probabilistic framework based on Hierarchical Bloom Filter (HBF) architectures to address these limitations across biometric and hardware domains. The first contribution establishes the Dynamic Hierarchical Bloom Filter (DHBF) as a noise-tolerant and dynamically updatable authentication structure for large-scale biometrics. Unlike static Bloom-based systems that require reconstruction upon updates, DHBF supports enrollment, querying, insertion and deletion without structural rebuild. Experimental evaluation on 30,000 facial biometric templates demonstrates 100% enrollment and query accuracy, including robust acceptance of noisy biometric inputs while maintaining correct rejection of non-enrolled identities. These results validate that hierarchical probabilistic encoding can preserve both scalability and authentication reliability in practical deployments. Building on this foundation, Bio-BloomChain integrates DHBF into a blockchain-based smart contract framework to provide tamper-evident, privacy-preserving biometric lifecycle management. The system stores only hashed and non-invertible commitments on-chain while maintaining probabilistic verification logic within the contract layer. Large-scale evaluation again reports 100% enrollment, insertion, query and deletion accuracy across 30,000 templates, therefore, solving the existing problem of blockchains being able to authenticate noisy data. Moreover, the deployment analysis shows that execution on Polygon zkEVM reduces operational costs by several orders of magnitude compared to Ethereum, therefore, bringing enrollment and deletion costs below $0.001 per operation which demonstrate the feasibility of scalable blockchain biometric authentication in practice. Finally, the hierarchical probabilistic paradigm is extended to electronic hardware authentication through the Persistent Hierarchical Bloom Filter (PHBF). Applied to electronic fingerprints derived from physical unclonable functions (PUFs), PHBF demonstrates robust authentication under environmental variations such as temperature-induced noise. Experimental results show zero-error operation at the selected decision threshold and substantial system-level improvements as well as over 10^5 faster query processing and significantly reduced storage requirements compared to large scale tracking.