Author name cluster

Ping He

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

AAAI Conference 2026 Conference Paper

Better Datasets Start from RefineLab: Automatic Optimization for High-Quality Dataset Refinement

Xiaonan Luo
Yue Huang
Ping He
Xiangliang Zhang

High‑quality Question–Answer (QA) datasets are foundational for reliable Large Language Model (LLM) evaluation, yet even expert‑crafted datasets exhibit persistent gaps in domain coverage, misaligned difficulty distributions, and factual inconsistencies. The recent surge in generative model-powered datasets has compounded these quality challenges. In this work, we introduce RefineLab, the first LLM‑driven framework that automatically refines raw QA textual data into high-quality datasets under a controllable token‑budget constraint. RefineLab takes a set of target quality attributes as refinement objectives and performs selective edits within a predefined token budget to ensure practicality and efficiency. In essence, RefineLab addresses a constrained optimization problem: improving the quality of QA samples as much as possible while respecting resource limitations. With a set of available refinement operations, RefineLab takes as input the original dataset, a specified set of target quality dimensions, and a token budget, and determines which refinement operations should be applied to each QA sample. This process is guided by an assignment module that selects optimal refinement strategies to maximize overall dataset quality while adhering to the budget constraint. Experiments demonstrate that RefineLab consistently narrows divergence from expert datasets across coverage, difficulty alignment, factual fidelity, and distractor quality. RefineLab pioneers a scalable, customizable path to reproducible dataset design, with broad implications for LLM evaluation.

PDF Details DOI

AAAI Conference 2026 Conference Paper

HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors

Jingxiao Yang
Ping He
Tianyu Du
Sun Bing
Xuhong Zhang

Recent advances in software vulnerability detection have been driven by Language Model (LM)-based approaches. However, these models remain vulnerable to adversarial attacks that exploit lexical and syntax perturbations, allowing critical flaws to evade detection. Existing black-box attacks on LM-based vulnerability detectors primarily rely on isolated perturbation strategies, limiting their ability to efficiently explore the adversarial code space for optimal perturbations. To bridge this gap, we propose HogVul, a black-box adversarial code generation framework that integrates both lexical and syntax perturbations under a unified dual-channel optimization strategy driven by Particle Swarm Optimization (PSO). By systematically coordinating two-level perturbations, HogVul effectively expands the search space for adversarial examples, enhancing the attack efficacy. Extensive experiments on four benchmark datasets demonstrate that HogVul achieves an average attack success rate improvement of 26.05% over state-of-the-art baseline methods. These findings highlight the potential of hybrid optimization strategies in exposing model vulnerabilities.

PDF Details DOI

AAAI Conference 2026 Conference Paper

S3Net: Spatiotemporally Separated Sparse Network for Neuromorphic Vision Processing

Ping He
Rong Xiao
Wanying Xu
Chenwei Tang
Shudong Huang
Huajin Tang

Dynamic Vision Sensor (DVS) asynchronously records sparse events triggered by changes in pixel intensity, offering high temporal resolution and low latency. Existing frame-based methods process event data densely, violating its inherent sparsity and introducing computational redundancy. While asynchronous models preserve the event stream's native format, they often neglect spatial information, compromising their adaptability and efficiency. To address these limitations, we propose a Spatiotemporally Separated Sparse Network (S3Net) for efficient event stream encoding and learning. Specifically, we employ a learnable sparse encoding scheme to construct a voxel-structured representation that effectively extracts spatiotemporal relationships among event data. After that, we propose a dual-branch architecture to capture localized spatial dependencies and dynamic temporal patterns of event data. By explicitly decoupling spatial and temporal modeling, S3Net enables end-to-end asynchronous processing of variable-length event sequences, achieving both strong representational capacity and high computational efficiency. Experimental results on six event-based datasets demonstrate that S3Net achieves state-of-the-art performance. Compared to frame-based methods, it significantly reduces computational overhead and model complexity, while also outperforming existing asynchronous approaches in inference speed without compromising accuracy. Extensive experiments across six event-based datasets show that S3Net establishes new state-of-the-art performance. Our method reduces computational costs by 35% and model parameters by 27% compared to frame-based approaches, while delivering 1.58× faster inference than existing point-based methods at comparable accuracy levels.

PDF Details DOI

JBHI Journal 2025 Journal Article

3MT-Net: A Multi-Modal Multi-Task Model for Breast Cancer and Pathological Subtype Classification Based on a Multicenter Study

Yaofei Duan
Patrick Cheong-Iao Pang
Ping He
Rongsheng Wang
Yue Sun
Chuntao Liu
Xiaorong Zhang
Xirong Yuan

Breast cancer poses a significant threat to women's health, and ultrasound plays a critical role in the assessment of breast lesions. This study introduces a prospective deep learning architecture, termed the “Multi-modal Multi-task Network” (3MT-Net), which integrates clinical data with B-mode and color Doppler ultrasound images. Specifically, an AM-CapsNet is employed to extract key features from ultrasound images, while a cascaded cross-attention mechanism is utilized to fuse clinical data. Moreover, an ensemble learning approach with an optimization algorithm is adopted to dynamically assign weights to different modalities, accommodating both high-dimensional and low-dimensional data. The 3MT-Net performs binary classification of benign versus malignant lesions and further classifies the pathological subtypes. Data were retrospectively collected from nine medical centers to ensure the broad applicability of the 3MT-Net. Two separate testsets were created and extensive experiments were conducted. Comparative analyses demonstrated that the AUC of the 3MT-Net outperforms the industry-standard computer-aided detection product, S-Detect, by 1. 4% to 3. 8%.

Details DOI

ICLR Conference 2024 Conference Paper

BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection

Tinghao Xie
Xiangyu Qi
Ping He
Yiming Li
Jiachen T. Wang
Prateek Mittal

We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs. Our defense falls within the category of post-development defenses that operate independently of how the model was generated. The proposed defense is built upon a novel reverse engineering approach that can directly extract **backdoor functionality** of a given backdoored model to a *backdoor expert* model. The approach is straightforward --- finetuning the backdoored model over a small set of intentionally mislabeled clean samples, such that it unlearns the normal functionality while still preserving the backdoor functionality, and thus resulting in a model~(dubbed a backdoor expert model) that can only recognize backdoor inputs. Based on the extracted backdoor expert model, we show the feasibility of devising highly accurate backdoor input detectors that filter out the backdoor inputs during model inference. Further augmented by an ensemble strategy with a finetuned auxiliary model, our defense, **BaDExpert** (**Ba**ckdoor Input **D**etection with Backdoor **Expert**), effectively mitigates 17 SOTA backdoor attacks while minimally impacting clean utility. The effectiveness of BaDExpert has been verified on multiple datasets (CIFAR10, GTSRB and ImageNet) across various model architectures (ResNet, VGG, MobileNetV2 and Vision Transformer). Our code is integrated into our research toolbox: [https://github.com/vtu81/backdoor-toolbox](https://github.com/vtu81/backdoor-toolbox).

Details

JBHI Journal 2020 Journal Article

Automatic Identification of Breast Ultrasound Image Based on Supervised Block-Based Region Segmentation Algorithm and Features Combination Migration Deep Learning Model

Wen-Xuan Liao
Ping He
Jin Hao
Xuan-Yu Wang
Ruo-Lin Yang
Dong An
Li-Gang Cui

Breast cancer is a high-incidence type of cancer for women. Early diagnosis plays a crucial role in the successful treatment of the disease and the effective reduction of deaths. In this paper, deep learning technology combined with ultrasound imaging diagnosis was used to identify and determine whether the tumors were benign or malignant. First, the tumor regions were segmented from the breast ultrasound (BUS) images using the supervised block-based region segmentation algorithm. Then, a VGG-19 network pretrained on the ImageNet dataset was applied to the segmented BUS images to predict whether the breast tumor was benign or malignant. The benchmark data for bio-validation were obtained from 141 patients with 199 breast tumors, including 69 cases of malignancy and 130 cases of benign tumors. The experiment showed that the accuracy of the supervised block-based region segmentation algorithm was almost the same as that of manual segmentation; therefore, it can replace manual work. The diagnostic effect of the combination feature model established based on the depth feature of the B-mode ultrasonic imaging and strain elastography was better than that of the model established based on these two images alone. The correct recognition rate was 92. 95%, and the AUC was 0. 98 for the combination feature model.

Details DOI