Fang Yu

Yu-Hang Chien, Fang Yu

Sports professionals constantly under pressure to perform at the highest level can benefit from sports analysis, which allows coaches and players to reduce manual efforts and systematically evaluate their performance using automated tools. This research aims to advance sports analysis in badminton, systematically detecting hit-frames automatically from match videos using modern deep learning techniques. The data included in hit-frames can subsequently be utilized to synthesize players' strokes and on-court movement, as well as for other downstream applications such as analyzing training tasks and competition strategy. The proposed approach in this study comprises several automated procedures like rally-wise video trimming, player and court keypoints detection, shuttlecock flying direction prediction, and hit-frame detection. In the study, we achieved 99% accuracy on shot angle recognition for video trimming, over 92% accuracy for applying player keypoints sequences on shuttlecock flying direction prediction, and reported the evaluation results of rally-wise video trimming and hit-frame detection.

Shang-Jung Wen, Jia-Ming Chang, Fang Yu

High-dimensional single-cell data poses significant challenges in identifying underlying biological patterns due to the complexity and heterogeneity of cellular states. We propose a comprehensive gene-cell dependency visualization via unsupervised clustering, Growing Hierarchical Self-Organizing Map (GHSOM), specifically designed for analyzing high-dimensional single-cell data like single-cell sequencing and CRISPR screens. GHSOM is applied to cluster samples in a hierarchical structure such that the self-growth structure of clusters satisfies the required variations between and within. We propose a novel Significant Attributes Identification Algorithm to identify features that distinguish clusters. This algorithm pinpoints attributes with minimal variation within a cluster but substantial variation between clusters. These key attributes can then be used for targeted data retrieval and downstream analysis. Furthermore, we present two innovative visualization tools: Cluster Feature Map and Cluster Distribution Map. The Cluster Feature Map highlights the distribution of specific features across the hierarchical structure of GHSOM clusters. This allows for rapid visual assessment of cluster uniqueness based on chosen features. The Cluster Distribution Map depicts leaf clusters as circles on the GHSOM grid, with circle size reflecting cluster data size and color customizable to visualize features like cell type or other attributes. We apply our analysis to three single-cell datasets and one CRISPR dataset (cell-gene database) and evaluate clustering methods with internal and external CH and ARI scores. GHSOM performs well, being the best performer in internal evaluation (CH=4.2). In external evaluation, GHSOM has the third-best performance of all methods.

Ming-I Huang, Chih-Duo Hong, Fang Yu

This paper introduces PyFair, a formal framework for evaluating and verifying individual fairness of Deep Neural Networks (DNNs). By adapting the concolic testing tool PyCT, we generate fairness-specific path constraints to systematically explore DNN behaviors. Our key innovation is a dual network architecture that enables comprehensive fairness assessments and provides completeness guarantees for certain network types. We evaluate PyFair on 25 benchmark models, including those enhanced by existing bias mitigation techniques. Results demonstrate PyFair's efficacy in detecting discriminatory instances and verifying fairness, while also revealing scalability challenges for complex models. This work advances algorithmic fairness in critical domains by offering a rigorous, systematic method for fairness testing and verification of pre-trained DNNs.

Jerry Wang, Fang Yu

Adversarial prompt attacks can significantly alter the reliability of Retrieval-Augmented Generation (RAG) systems by re-ranking them to produce incorrect outputs. In this paper, we present a novel method that applies Differential Evolution (DE) to optimize adversarial prompt suffixes for RAG-based question answering. Our approach is gradient-free, treating the RAG pipeline as a black box and evolving a population of candidate suffixes to maximize the retrieval rank of a targeted incorrect document to be closer to real world scenarios. We conducted experiments on the BEIR QA datasets to evaluate attack success at certain retrieval rank thresholds under multiple retrieving applications. Our results demonstrate that DE-based prompt optimization attains competitive (and in some cases higher) success rates compared to GGPP to dense retrievers and PRADA to sparse retrievers, while using only a small number of tokens (<=5 tokens) in the adversarial suffix. Furthermore, we introduce a readability-aware suffix construction strategy, validated by a statistically significant reduction in MLM negative log-likelihood with Welch's t-test. Through evaluations with a BERT-based adversarial suffix detector, we show that DE-generated suffixes evade detection, yielding near-chance detection accuracy.

Hsin-Ling Hsu, Min-Yu Chen, Nai-Chia Chen et al.

Transformer-based NLP models remain vulnerable to adversarial perturbations, yet existing repair methods face a fundamental trade-off: gradient-based approaches offer flexibility but lack verifiability and often overfit; methods that do provide repair guarantees are restricted to the final layer or small networks, significantly limiting the parameter search space available for repair. We present WARP (Weight-Adjusted Repair with Provability), a constraint-based repair framework that extends repair beyond the last layer of Transformer models. WARP formulates repair as a convex quadratic program derived from a first-order linearization of the logit gap, enabling tractable optimization over a high-dimensional parameter space. Under the condition that the first-order approximation holds, this formulation induces three per-sample guarantees: (i) a positive margin constraint ensuring correct classification on repaired inputs, (ii) preservation constraints over a designated remain set, and (iii) a certified robustness radius derived from Lipschitz continuity. To ensure feasibility across varying model architectures, we introduce a sensitivity-based preprocessing step that conditions the optimization landscape accordingly. We further show that the iterative optimization procedure converges to solutions satisfying all repair constraints under mild assumptions. Empirical evaluation on encoder-only Transformers with varying layer architectures validates that these guarantees hold in practice while improving robustness to adversarial inputs. Our results demonstrate that guaranteed, generalizable Transformer repair is achievable through principled constraint-based optimization.

Chih-Duo Hong, Yu Wang, Yao-Chen Chang et al.

Concolic testing for deep neural networks alternates concrete execution with constraint solving to search for inputs that flip decisions. We present an {influence-guided} concolic tester for Transformer classifiers that ranks path predicates by SHAP-based estimates of their impact on the model output. To enable SMT solving on modern architectures, we prototype a solver-compatible, pure-Python semantics for multi-head self-attention and introduce practical scheduling heuristics that temper constraint growth on deeper models. In a white-box study on compact Transformers under small $L_0$ budgets, influence guidance finds label-flip inputs more efficiently than a FIFO baseline and maintains steady progress on deeper networks. Aggregating successful attack instances with a SHAP-based critical decision path analysis reveals recurring, compact decision logic shared across attacks. These observations suggest that (i) influence signals provide a useful search bias for symbolic exploration, and (ii) solver-friendly attention semantics paired with lightweight scheduling make concolic testing feasible for contemporary Transformer models, offering potential utility for debugging and model auditing.

Zitao Shen, Yoonkwon Yi, Anusha Bompelli et al.

Since no effective therapies exist for Alzheimer's disease (AD), prevention has become more critical through lifestyle factor changes and interventions. Analyzing electronic health records (EHR) of patients with AD can help us better understand lifestyle's effect on AD. However, lifestyle information is typically stored in clinical narratives. Thus, the objective of the study was to demonstrate the feasibility of natural language processing (NLP) models to classify lifestyle factors (e.g., physical activity and excessive diet) from clinical texts. We automatically generated labels for the training data by using a rule-based NLP algorithm. We conducted weak supervision for pre-trained Bidirectional Encoder Representations from Transformers (BERT) models on the weakly labeled training corpus. These models include the BERT base model, PubMedBERT(abstracts + full text), PubMedBERT(only abstracts), Unified Medical Language System (UMLS) BERT, Bio BERT, and Bio-clinical BERT. We performed two case studies: physical activity and excessive diet, in order to validate the effectiveness of BERT models in classifying lifestyle factors for AD. These models were compared on the developed Gold Standard Corpus (GSC) on the two case studies. The PubmedBERT(Abs) model achieved the best performance for physical activity, with its precision, recall, and F-1 scores of 0.96, 0.96, and 0.96, respectively. Regarding classifying excessive diet, the Bio BERT model showed the highest performance with perfect precision, recall, and F-1 scores. The proposed approach leveraging weak supervision could significantly increase the sample size, which is required for training the deep learning models. The study also demonstrates the effectiveness of BERT models for extracting lifestyle factors for Alzheimer's disease from clinical notes.

Fang Yu, Daowen Qiu, Xiaoming Wang et al.

New quantum private database (with N elements) query protocols are presented and analyzed. Protocols preserve O(logN) communication complexity of known protocols for the same task, but achieve several significant improvements in security, especially concerning user privacy. For example, the randomized form of our protocol has a cheat-sensitive property - it allows the user to detect a dishonest database with a nonzero probability, while the phase-encoded private query protocols for the same task do not have such a property. Moreover, when the database performs the computational basis measurement, a particular projective measurement which can cause a significant loss of user privacy in the previous private query protocols with O(logN) communication complexity, at most half of the user privacy could leak to such a database in our protocol, while in the QPQ protocol, the entire user privacy could leak out. In addition, it is proved here that for large N, the user could detect a cheating via the computational basis measurement, with a probability close to 1/2 using O(\sqrt{N}) special queries. Finally, it is shown here, for both forms of our protocol, basic and randomized, how a dishonest database has to act in case it could not learn user's queries.