Institution profile

York University

Academic institutionnorthamerica · ca
Official website
Research library372linked papers
Opportunities0open roles
Selected work

Representative Papers

Secret Breach Prevention in Software Issue Reports

Oct 31, 2024arXiv.org

This study addresses the previously unexplored problem of inadvertent leakage of sensitive information—such as API keys and authentication tokens—in GitHub issue reports. To overcome the lack of benchmark datasets and effective detection methods for this scenario, we introduce the first large-scale, manually annotated benchmark containing 5,800 real-world secrets. We propose a lightweight hybrid detection paradigm that synergistically combines regex-based extraction with large language model (LLM)-driven contextual classification. Our method integrates entropy analysis, RoBERTa/CodeBERT feature encoding, and fine-tuned Qwen/LLaMA models, augmented by GPT-4o few-shot learning to enhance generalization. Evaluated on our benchmark, the approach achieves an F1 score of 94.49%; it further attains 81.6% F1 across 178 real-world repositories, significantly outperforming conventional entropy- and keyword-based baselines. This work establishes the first dedicated framework for detecting secret leakage in issue reports, demonstrating the superiority of open-source LLM fine-tuning for this task.

2 citationsRead paper

Unsupervised Text Segmentation via Kernel Change-Point Detection on Sentence Embeddings

Jan 26, 2026

This work addresses the challenges of high annotation costs, subjectivity, and poor cross-domain generalization in unsupervised text segmentation by proposing a training-free automatic segmentation method. The approach maps sentences into embedding vectors and applies kernel change point detection (KCPD) with a penalty term to identify segment boundaries. Its key innovation lies in establishing, for the first time, a dependency-aware theoretical framework for KCPD under m-dependent sequences that accounts for the short-range dependencies inherent in natural language, providing provable upper bounds on total risk and guarantees for change point localization. A controllable synthetic data validation framework based on large language models is also introduced. Experiments demonstrate that the method outperforms strong unsupervised baselines on standard benchmarks and validates its theoretical soundness and practical efficacy in a case study on Taylor Swift’s tweets.

1 citationsRead paper

Enhanced Multiuser CSI-Based Physical Layer Authentication Based on Information Reconciliation

Feb 01, 2025IEEE Wireless Communications Letters

To address the insufficient robustness and excessive overhead of physical-layer authentication in low-power IoT multi-user scenarios, this paper proposes a channel state information (CSI)-based information reconciliation authentication scheme. The method innovatively incorporates the Slepian–Wolf distributed source coding principle into a time-varying multi-user CSI authentication framework, integrating adaptive quantization with polar codes to achieve efficient, low-overhead information reconciliation. Temporal alignment of multi-user channel measurements and variable-bit quantization further enhance authentication consistency and interference resilience. Experimental results demonstrate a detection probability exceeding 99.80% at an extremely low false alarm rate (<10⁻⁴), significantly outperforming existing approaches. This work establishes a new paradigm for highly reliable, cost-effective physical-layer authentication tailored to resource-constrained IoT deployments.

1 citationsRead paper

The Impact of Unstated Norms in Bias Analysis of Language Models

Apr 04, 2024arXiv.org

This paper identifies a systematic mismatch between mainstream template-based counterfactual bias detection methods—which explicitly annotate group identities (e.g., “Black president” vs. “White president”)—and implicit linguistic norms (e.g., markedness: *Black president* is marked, while *president* defaults to White) inherent in pretraining corpora. This mismatch distorts bias measurement, notably inflating perceived negativity toward White-associated texts. Through controlled experiments, formal modeling of linguistic norms, and empirical evaluation, the study is the first to uncover how unannotated norms—particularly markedness—confound bias quantification, thereby challenging the validity of templated evaluation. Its contributions are threefold: (1) establishing implicit linguistic norms as critical confounding variables in bias measurement; (2) proposing a more natural, minimally interventionist evaluation paradigm; and (3) providing theoretical foundations and concrete pathways for developing robust, norm-aware bias quantification methods.

1 citationsRead paper
Recent publications

Latest Papers