Publications (68)
TraceRAG: A LLM-Based Framework for Explainable Android Malware Detection and Behavior Analysis
Guangyu Zhang, Xixuan Wang, Shiyu Sun +3
Sophisticated evasion tactics in malicious Android applications, combined with their intricate behavioral semantics, enable attackers to conceal malicious logic within legitimate f…
SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration
Zhi Chen, Kun Sun, Fan Yang +1
In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR. Firstly, we pro…
End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning
Qiaoyu Zheng, Yuze Sun, Chaoyi Wu +8
The integration of Large Language Models (LLMs) into healthcare is constrained by knowledge limitations, hallucinations, and a disconnect from Evidence-Based Medicine (EBM). While…
A Novel Dependency Framework for Enhancing Discourse Data Analysis
Kun Sun, Rong Wang
The development of different theories of discourse structure has led to the establishment of discourse corpora based on these theories. However, the existence of discourse corpora…
Compensating Removed Frequency Components: Thwarting Voice Spectrum Reduction Attacks
Shu Wang, Kun Sun, Qi Li
Automatic speech recognition (ASR) provides diverse audio-to-text services for humans to communicate with machines. However, recent research reveals ASR systems are vulnerable to v…
Off-Path TCP Hijacking in Wi-Fi Networks: A Packet-Size Side Channel Attack
Ziqiang Wang, Xuewei Feng, Qi Li +6
In this paper, we unveil a fundamental side channel in Wi-Fi networks, specifically the observable frame size, which can be exploited by attackers to conduct TCP hijacking attacks.…
TYPEPULSE: Detecting Type Confusion Bugs in Rust Programs
Hung-Mao Chen, Xu He, Shu Wang +2
Rust supports type conversions and safe Rust guarantees the security of these conversions through robust static type checking and strict ownership guidelines. However, there are in…
Exploiting Cross-Layer Vulnerabilities: Off-Path Attacks on the TCP/IP Protocol Suite
Xuewei Feng, Qi Li, Kun Sun +2
After more than 40 years of development, the fundamental TCP/IP protocol suite, serving as the backbone of the Internet, is widely recognized for having achieved an elevated level…
Having Difficulty Understanding Manuals? Automatically Converting User Manuals into Instructional Videos
Songsong Liu, Shu Wang, Kun Sun
While users tend to perceive instructional videos as an experience rather than a lesson with a set of instructions, instructional videos are more effective and appealing than textu…
Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic
Yuqi Qing, Qilei Yin, Xinhao Deng +6
Machine learning (ML) is promising in accurately detecting malicious flows in encrypted network traffic; however, it is challenging to collect a training dataset that contains a su…
Towards Fine-Grained Webpage Fingerprinting at Scale
Xiyuan Zhao, Xinhao Deng, Qi Li +4
Website Fingerprinting (WF) attacks can effectively identify the websites visited by Tor clients via analyzing encrypted traffic patterns. Existing attacks focus on identifying dif…
Textual Similarity as a Key Metric in Machine Translation Quality Estimation
Kun Sun, Rong Wang
Machine Translation (MT) Quality Estimation (QE) assesses translation reliability without reference texts. This study introduces "textual similarity" as a new metric for QE, using…
When the Differences in Frequency Domain are Compensated: Understanding and Defeating Modulated Replay Attacks on Automatic Speech Recognition
Shu Wang, Jiahao Cao, Xu He +2
Automatic speech recognition (ASR) systems have been widely deployed in modern smart devices to provide convenient and diverse voice-controlled services. Since ASR systems are vuln…
MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency
Qiao Wu, Jiaqi Yang, Kun Sun +3
3D single object tracking (SOT) is an indispensable part of automated driving. Existing approaches rely heavily on large, densely labeled datasets. However, annotating point clouds…
GPU Accelerated Cascade Hashing Image Matching for Large Scale 3D Reconstruction
Tao Xu, Kun Sun, Wenbing Tao
Image feature point matching is a key step in Structure from Motion(SFM). However, it is becoming more and more time consuming because the number of images is getting larger and la…
Knowledge-enhanced Pretraining for Vision-language Pathology Foundation Model on Cancer Diagnosis
Xiao Zhou, Luoyi Sun, Dexuan He +10
Vision-language foundation models have shown great promise in computational pathology but remain primarily data-driven, lacking explicit integration of medical knowledge. We introd…
Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need
Yuqi Bai, Tianyu Huang, Kun Sun +1
This research focuses on using large language models (LLMs) to simulate social experiments, exploring their ability to emulate human personality in virtual persona role-playing. Th…
BinGo: Identifying Security Patches in Binary Code with Graph Representation Learning
Xu He, Shu Wang, Pengbin Feng +4
A timely software update is vital to combat the increasing security vulnerabilities. However, some software vendors may secretly patch their vulnerabilities without creating CVE en…
Off-Path TCP Exploits of the Mixed IPID Assignment
Xuewei Feng, Chuanpu Fu, Qi Li +2
In this paper, we uncover a new off-path TCP hijacking attack that can be used to terminate victim TCP connections or inject forged data into victim TCP connections by manipulating…
4D Cardiac Ultrasound Standard Plane Location by Spatial-Temporal Correlation
Yun Gu, Guang-Zhong Yang, Jie Yang +1
Echocardiography plays an important part in diagnostic aid in cardiac diseases. A critical step in echocardiography-aided diagnosis is to extract the standard planes since they ten…
A Hard Label Black-box Adversarial Attack Against Graph Neural Networks
Jiaming Mu, Binghui Wang, Qi Li +3
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in various graph structure related tasks such as node classification and graph classification. However, GNNs…
Object Detection in Hyperspectral Image via Unified Spectral-Spatial Feature Aggregation
Xiao He, Chang Tang, Xinwang Liu +3
Deep learning-based hyperspectral image (HSI) classification and object detection techniques have gained significant attention due to their vital role in image content analysis, in…
Dye4AI: Assuring Data Boundary on Generative AI Services
Shu Wang, Kun Sun, Yan Zhai
Generative artificial intelligence (AI) is versatile for various applications, but security and privacy concerns with third-party AI vendors hinder its broader adoption in sensitiv…
Prompt Overflow: What the Guardrail Inspects Is Not What the Model Infers
Yuanbo Zhou, Changjia Zhu, Junyu Wang +5
Guardrail models (a.k.a. safety checkers) are widely deployed to screen user inputs before they reach large language models (LLMs), serving as a primary defense against prompt inje…
Continuous Output Personality Detection Models via Mixed Strategy Training
Rong Wang, Kun Sun
The traditional personality models only yield binary results. This paper presents a novel approach for training personality detection models that produce continuous output values,…
Off-Path TCP Exploits: PMTUD Breaks TCP Connection Isolation in IP Address Sharing Scenarios
Xuewei Feng, Zhaoxi Li, Qi Li +3
Path MTU Discovery (PMTUD) and IP address sharing are integral aspects of modern Internet infrastructure. In this paper, we investigate the security vulnerabilities associated with…
Differential contributions of machine learning and statistical analysis to language and cognitive sciences
Kun Sun, Rong Wang
Data-driven approaches have revolutionized scientific research, with machine learning and statistical analysis being commonly used methodologies. Despite their widespread use, thes…
Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs
Rong Wang, Kun Sun, Jonas Kuhn
Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often struggle with spatial reasoning. This paper presents a novel neural-symb…
From Hardware Fingerprint to Access Token: Enhancing the Authentication on IoT Devices
Yue Xiao, Yi He, Xiaoli Zhang +5
The proliferation of consumer IoT products in our daily lives has raised the need for secure device authentication and access control. Unfortunately, these resource-constrained dev…
Contextual Semantic Relevance Tracks fMRI BOLD Responses During Naturalistic Speech Comprehension
Kun Sun, Rong Wang
Naturalistic language comprehension requires listeners to process both local probabilistic expectations and contextual semantic relations. This study tested whether contextual sema…
Exploiting Sequence Number Leakage: TCP Hijacking in NAT-Enabled Wi-Fi Networks
Yuxiang Yang, Xuewei Feng, Qi Li +3
In this paper, we uncover a new side-channel vulnerability in the widely used NAT port preservation strategy and an insufficient reverse path validation strategy of Wi-Fi routers,…
Automatic Essay Multi-dimensional Scoring with Fine-tuning and Multiple Regression
Kun Sun, Rong Wang
Automated essay scoring (AES) involves predicting a score that reflects the writing quality of an essay. Most existing AES systems produce only a single overall score. However, use…
ReDAN: An Empirical Study on Remote DoS Attacks against NAT Networks
Xuewei Feng, Yuxiang Yang, Qi Li +6
In this paper, we conduct an empirical study on remote DoS attacks targeting NAT networks. We show that Internet attackers operating outside local NAT networks can remotely identif…
When Genes Speak: A Semantic-Guided Framework for Spatially Resolved Transcriptomics Data Clustering
Jiangkai Long, Yanran Zhu, Chang Tang +3
Spatial transcriptomics enables gene expression profiling with spatial context, offering unprecedented insights into the tissue microenvironment. However, most computational models…
ChainMarks: Securing DNN Watermark with Cryptographic Chain
Brian Choi, Shu Wang, Isabelle Choi +1
With the widespread deployment of deep neural network (DNN) models, dynamic watermarking techniques are being used to protect the intellectual property of model owners. However, re…
3D Single-object Tracking in Point Clouds with High Temporal Variation
Qiao Wu, Kun Sun, Pei An +3
The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of t…
Systematic Framework of Application Methods for Large Language Models in Language Sciences
Kun Sun, Rong Wang
Large Language Models (LLMs) are transforming language sciences. However, their widespread deployment currently suffers from methodological fragmentation and a lack of systematic s…
Bridging the Gap: A Study of AI-based Vulnerability Management between Industry and Academia
Shengye Wan, Joshua Saxe, Craig Gomes +4
Recent research advances in Artificial Intelligence (AI) have yielded promising results for automated software vulnerability management. AI-based models are reported to greatly out…
Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding
Jianghao Yin, Qingbin Li, Kun Sun +10
While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image…
A Systematic Study of Android Non-SDK (Hidden) Service API Security
Yi He, Yacong Gu, Purui Su +4
Android allows apps to communicate with its system services via system service helpers so that these apps can use various functions provided by the system services. Meanwhile, the…
TIMIT Speaker Profiling: A Comparison of Multi-task learning and Single-task learning Approaches
Rong Wang, Kun Sun
This study employs deep learning techniques to explore four speaker profiling tasks on the TIMIT dataset, namely gender classification, accent classification, age estimation, and s…
Agentic Society: Merging skeleton from real world and texture from Large Language Model
Yuqi Bai, Kun Sun, Huishi Yin
Recent advancements in large language models (LLMs) and agent technologies offer promising solutions to the simulation of social science experiments, but the availability of data o…
Contextual Semantic Relevance and Word Surprisal Predict N400 and P600 Dynamics During Naturalistic Reading
Kun Sun, Rong Wang
Word surprisal is a well-established computational predictor of human neural responses during language comprehension, but it remains less clear whether local semantic fit explains…
Prior over Evidence: Stereotype-Driven Diagnosis in LLM-Based L2 Pronunciation Feedback
Rong Wang, Kun Sun
Large language models are increasingly deployed for written pronunciation feedback in second-language (L2) English learning, under the assumption that their diagnoses are grounded…
The fragility of "cultural tendencies" in LLMs
Kun Sun, Rong Wang
In a recent study, Lu, Song, and Zhang (2025) (LSZ) propose that large language models (LLMs), when prompted in different languages, display culturally specific tendencies. They re…
An Agentic System for Rare Disease Diagnosis with Traceable Reasoning
Weike Zhao, Chaoyi Wu, Yanjie Fan +10
Rare diseases affect over 300 million individuals worldwide, yet timely and accurate diagnosis remains an urgent challenge. Patients often endure a prolonged diagnostic odyssey exc…
Boosting Pathology Foundation Models via Few-shot Prompt-tuning for Rare Cancer Subtyping
Dexuan He, Xiao Zhou, Wenbin Guan +11
Rare cancers comprise 20-25% of all malignancies but face major diagnostic challenges due to limited expert availability-especially in pediatric oncology, where they represent over…
Shortcut to adiabatic control of soliton matter waves by tunable interaction
Jing Li, Kun Sun, Xi Chen
We propose a method for shortcut to adiabatic control of soliton matter waves in harmonic traps. The tunable interaction controlled by Feshbach resonance is inversely designed to a…
NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables
Yilin Li, Guozhu Meng, Mingyang Sun +4
On-device deep learning models have extensive real world demands. Deep learning compilers efficiently compile models into executables for deployment on edge devices, but these exec…
STATE: A Robust ATE Estimator of Heavy-Tailed Metrics for Variance Reduction in Online Controlled Experiments
Hao Zhou, Kun Sun, Shaoming Li +4
Online controlled experiments play a crucial role in enabling data-driven decisions across a wide range of companies. Variance reduction is an effective technique to improve the se…
Attention-aware semantic relevance predicting Chinese sentence reading
Kun Sun
In recent years, several influential computational models and metrics have been proposed to predict how humans comprehend and process sentence. One particularly promising approach…
Detecting Localized Adversarial Examples: A Generic Approach using Critical Region Analysis
Fengting Li, Xuankai Liu, Xiaoli Zhang +3
Deep neural networks (DNNs) have been applied in a wide range of applications,e.g.,face recognition and image classification; however,they are vulnerable to adversarial examples. B…
SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement with Multi-Scale Perception
Qi Qi, Kunqian Li, Haiyong Zheng +3
Due to the wavelength-dependent light attenuation, refraction and scattering, underwater images usually suffer from color distortion and blurred details. However, due to the limite…
The Roles of Contextual Semantic Relevance Metrics in Human Visual Processing
Kun Sun, Rong Wang
Semantic relevance metrics can capture both the inherent semantics of individual objects and their relationships to other elements within a visual scene. Numerous previous research…
HSDreport: Heart Sound Diagnosis with Echocardiography Reports
Zihan Zhao, Pingjie Wang, Liudan Zhao +7
Heart sound auscultation holds significant importance in the diagnosis of congenital heart disease. However, existing methods for Heart Sound Diagnosis (HSD) tasks are predominantl…
Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI
Lei Zhou, Yuzhong Zhang, Jiadong Zhang +8
Automated breast tumor segmentation on the basis of dynamic contrast-enhancement magnetic resonance imaging (DCE-MRI) has shown great promise in clinical practice, particularly for…
Trilaminar Multiway Reconstruction Tree for Efficient Large Scale Structure from Motion
Kun Sun, Wenbing Tao
Accuracy and efficiency are two key problems in large scale incremental Structure from Motion (SfM). In this paper, we propose a unified framework to divide the image set into clus…
Computational Sentence-level Metrics Predicting Human Sentence Comprehension
Kun Sun, Rong Wang
The majority of research in computational psycholinguistics has concentrated on the processing of words. This study introduces innovative methods for computing sentence-level metri…
A Generalist Audio Foundation Model for Comprehensive Body Sound Auscultation
Pingjie Wang, Liudan Zhao, Zihan Zhao +6
Accurate and efficient auscultation-based diagnostics are vital for early disease detection, especially in resource-limited settings where specialized clinical expertise is scarce.…
UHR-Net: An Uncertainty-Aware Hypergraph Refinement Network for Medical Image Segmentation
Shuokun Cheng, Jinghao Shi, Kun Sun
Accurate lesion segmentation is crucial for clinical diagnosis and treatment planning. However, lesions often resemble surrounding tissues and exhibit ill-defined boundaries, leadi…
When Code Crosses Borders: A Security-Centric Study of LLM-based Code Translation
Hailong Chang, Guozhu Meng, Shuhui Xiao +3
Code translation is crucial for cross-language codebase migration, and large language models (LLMs) have emerged as a promising technique to automate this process. However, the sec…
SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems
Xu He, Di Wu, Yan Zhai +1
The rise of large language model (LLM)-based multi-agent systems (MAS) introduces new security and reliability challenges. While these systems show great promise in decomposing and…
Exploring Security Commits in Python
Shiyu Sun, Shu Wang, Xinda Wang +3
Python has become the most popular programming language as it is friendly to work with for beginners. However, a recent study has found that most security issues in Python have not…
PatchRNN: A Deep Learning-Based System for Security Patch Identification
Xinda Wang, Shu Wang, Pengbin Feng +4
With the increasing usage of open-source software (OSS) components, vulnerabilities embedded within them are propagated to a huge number of underlying applications. In practice, th…
Conceptual Design Report of Super Tau-Charm Facility: The Accelerator
Jiancong Bao, Anton Bogomyagkov, Zexin Cao +93
Electron-positron colliders operating in the GeV region of center-of-mass energies or the Tau-Charm energy region, have been proven to enable competitive frontier research, due to…
BlueSWAT: A Lightweight State-Aware Security Framework for Bluetooth Low Energy
Xijia Che, Yi He, Xuewei Feng +3
Bluetooth Low Energy (BLE) is a short-range wireless communication technology for resource-constrained IoT devices. Unfortunately, BLE is vulnerable to session-based attacks, where…
Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach
Kun Sun, Rong Wang, Anders Søgaard
Amidst the rapid evolution of LLMs, the significance of evaluation in comprehending and propelling these models forward is increasingly paramount. Evaluations have revealed that fa…
PathFix: Automated Program Repair with Expected Path
Xu He, Shu Wang, Kun Sun
Automated program repair (APR) techniques are effective in fixing inevitable defects in software, enhancing development efficiency and software robustness. However, due to the diff…