Publications (47)
Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging
Lin Lu, Zhigang Zuo, Ziji Sheng +1
Model merging has emerged as a promising approach for updating large language models (LLMs) by integrating multiple domain-specific models into a cross-domain merged model. Despite…
Comparative Analysis of Pre-trained Deep Learning Models and DINOv2 for Cushing's Syndrome Diagnosis in Facial Analysis
Hongjun Liu, Changwei Song, Jiaqi Qiang +7
Cushing's syndrome is a condition caused by excessive glucocorticoid secretion from the adrenal cortex, often manifesting with moon facies and plethora, making facial data crucial…
SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
Xueyang Zhou, Weidong Wang, Lin Lu +7
Large Language Model (LLM)-based agents are increasingly deployed in real-world applications such as "digital assistants, autonomous customer service, and decision-support systems"…
PCG-Informed Neural Solvers for High-Resolution Homogenization of Periodic Microstructures
Yu Xing, Yang Liu, Lipeng Chen +2
The mechanical properties of periodic microstructures are pivotal in various engineering applications. Homogenization theory is a powerful tool for predicting these properties by a…
FedDriveScore: Federated Scoring Driving Behavior with a Mixture of Metric Distributions
Lin Lu
Scoring the driving performance of various drivers on a unified scale, based on how safe or economical they drive on their daily trips, is essential for the driver profile task. Co…
Two-stage MR Image Segmentation Method for Brain Tumors based on Attention Mechanism
Li Zhu, Jiawei Jiang, Lin Lu +1
Multimodal magnetic resonance imaging (MRI) can reveal different patterns of human tissue and is crucial for clinical diagnosis. However, limited by cost, noise and manual labeling…
GFPack++: Improving 2D Irregular Packing by Learning Gradient Field with Attention
Tianyang Xue, Lin Lu, Yang Liu +5
2D irregular packing is a classic combinatorial optimization problem with various applications, such as material utilization and texture atlas generation. This NP-hard problem requ…
reslife: Residual Lifetime Analysis Tool in R
Zekai Wang, Andrew Crawford, Ka Lok Lee +2
Mean residual lifetime is an important measure utilized in various fields, including pharmaceutical companies, manufacturing companies, and insurance companies for survival analysi…
Conditional Testing based on Localized Conformal p-values
Xiaoyang Wu, Lin Lu, Zhaojun Wang +1
In this paper, we address conditional testing problems through the conformal inference framework. We define the localized conformal p-values by inverting prediction intervals and p…
GMT: A Geometric Multigrid Transformer Solver for Microstructure Homogenization
Yu Xing, Yang Liu, Tianyang Xue +1
Lattice metamaterials enable lightweight, multifunctional structures, yet homogenization-based evaluation of their effective properties remains computationally expensive. Neural su…
DualMS: Implicit Dual-Channel Minimal Surface Optimization for Heat Exchanger Design
Weizheng Zhang, Hao Pan, Lin Lu +4
Heat exchangers are critical components in a wide range of engineering applications, from energy systems to chemical processing, where efficient thermal management is essential. Th…
Monotonicity of the periodic waves for the perturbed generalized defocusing mKdV equation
Lin Lu, Aiyong Chen, Xiaokai He
In this paper, we study the existence of periodic waves for the perturbed generalized defocusing mKdV equation using the theory of geometric singular perturbation. By Abelian integ…
MIND: Microstructure INverse Design with Generative Hybrid Neural Representation
Tianyang Xue, Haochen Li, Longdu Liu +7
The inverse design of microstructures plays a pivotal role in optimizing metamaterials with specific, targeted physical properties. While traditional forward design methods are con…
Learning driving style embedding from GPS-derived moving patterns for driver identification
Lin Lu
Learning fingerprint-like driving style representations is crucial to accurately identify who is behind the wheel in open driving situations. This study explores the learning of dr…
Improving Artifact Robustness for CT Deep Learning Models Without Labeled Artifact Images via Domain Adaptation
Justin Cheung, Samuel Savine, Calvin Nguyen +2
If a CT scanner introduces a new artifact not present in the training labels, the model may misclassify the images. Although modern CT scanners include design features which mitiga…
Spectral analysis of small amplitude periodic -Novikov equation under transverse perturbations
Lin Lu, Xiaokai He, Aiyong Chen
This paper is devoted to the transverse stability problem for small-amplitude periodic traveling waves of the -Novikov equation, which arises as a two-dimensional extension of t…
Virtual Context: Enhancing Jailbreak Attacks with Special Token Injection
Yuqi Zhou, Lin Lu, Hanchi Sun +2
Jailbreak attacks on large language models (LLMs) involve inducing these models to generate harmful content that violates ethics or laws, posing a significant threat to LLM securit…
Stealing Training Data from Large Language Models in Decentralized Training through Activation Inversion Attack
Chenxi Dai, Lin Lu, Pan Zhou
Decentralized training has become a resource-efficient framework to democratize the training of large language models (LLMs). However, the privacy risks associated with this framew…
Study of a 43 day optical quasi-periodic oscillation for BL Lac S5 0716+714
Lin Lu, Hao-Jing Zhang, Guo-Wei Ren
The data for BL Lac object S5 0716+714 optical B, R and I bands are collected from November 10, 2017 to May 15, 2018. The raw data consists of 21396 quasi-simultaneous multi-band p…
Power Diagram Enhanced Adaptive Isosurface Extraction from Signed Distance Fields
Pengfei Wang, Ziyang Zhang, Wensong Wang +4
Extracting high-fidelity mesh surfaces from Signed Distance Fields has become a fundamental operation in geometry processing. Despite significant progress over the past decades, ke…
DeepMill: Neural Accessibility Learning for Subtractive Manufacturing
Fanchao Zhong, Yang Wang, Peng-Shuai Wang +2
Manufacturability is vital for product design and production, with accessibility being a key element, especially in subtractive manufacturing. Traditional methods for geometric acc…
Fake Generated Painting Detection via Frequency Analysis
Yong Bai, Yuanfang Guo, Jinjie Wei +3
With the development of deep neural networks, digital fake paintings can be generated by various style transfer algorithms.To detect the fake generated paintings, we analyze the fa…
Printed Perforated Lampshades for Continuous Projective Images
Haisen Zhao, Lin Lu, Yuan Wei +4
We present a technique for designing 3D-printed perforated lampshades, which project continuous grayscale images onto the surrounding walls. Given the geometry of the lampshade and…
Generalized Pole-Residue Method for Dynamic Analysis of Nonlinear Systems based on Volterra Series
Qianying Cao, Anteng Chang, Junfeng Du +1
Dynamic systems characterized by second-order nonlinear ordinary differential equations appear in many fields of physics and engineering. To solve these kinds of problems, time-con…
As-Continuous-As-Possible Extrusion Fabrication of Surface Models
Fanchao Zhong, Yonglai Xu, Haisen Zhao +1
We propose a novel computational framework for optimizing the toolpath continuity in fabricating surface models on an extrusion-based 3D printer. Toolpath continuity has been a cri…
MUSA-PINN: Multi-scale Weak-form Physics-Informed Neural Networks for Fluid Flow in Complex Geometries
Weizheng Zhang, Xunjie Xie, Hao Pan +4
The paper introduces MUSA-PINN, a multi-scale weak-form physics-informed neural network that enforces integral conservation laws over hierarchical spherical control volumes to impr…
AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design
Zhenyuan Zhao, Yu Xing, Tianyang Xue +3
Designing microstructures with coupled cross-physics objectives is a fundamental challenge where traditional topology optimization is often computationally prohibitive and deep gen…
Assessing the Health of Richibucto Estuary with the Latent Health Factor Index
Margaret Wu, Grace S. Chiu, Lin Lu
The ability to quantitatively assess the health of an ecosystem is often of great interest to those tasked with monitoring and conserving ecosystems. For decades, research in this…
A Platform for All-optical Thomson/ Compton Scattering with Versatile Parameters
Siyu Chen, Wenchao Yan, Mingyang Zhu +16
A dual-beam platform for all-optical electron-photon scattering, or Thomson/Compton scattering, with adjustable collision-angle and parameter tuning ability has been developed, whi…
Stochastic Porous Microstructures
Zhongren Wang, Lihao Tian, Xiaokang Liu +2
Stochastic porous structures are ubiquitous in natural phenomena and have gained considerable traction across diverse domains owing to their exceptional physical properties. The re…
A Multi-Agent Framework for Zero-Dimensional Reduced-Order Model Planning
Bingteng Sun, Hao Yin, Yiling Chen +9
The paper introduces Z-COPA, a multi‑agent framework that uses a symbolic graph engine and MILP‑guided optimization to automate the planning of zero‑dimensional reduced‑order model…
Modulational instability of small amplitude periodic traveling waves in the -family of Novikov equation
Xin Zhao, Lin Lu, Aiyong Chen
We study the modulational instability of smooth, small-amplitude periodic traveling wave solutions to the -family of Novikov equation with cubic nonlinearity with an arbitrary c…
Online Updating Statistics for Heterogenous Updating Regressions via Homogenization Techniques
Lin Lu, Lu Jun, Li Weiyu
Under the environment of big data streams, it is a common situation where the variable set of a model may change according to the condition of data streams. In this paper, we propo…
Methodology and Real-World Applications of Dynamic Uncertain Causality Graph for Clinical Diagnosis with Explainability and Invariance
Zhan Zhang, Qin Zhang, Yang Jiao +18
AI-aided clinical diagnosis is desired in medical care. Existing deep learning models lack explainability and mainly focus on image analysis. The recently developed Dynamic Uncerta…
Finite-difference-informed graph network for solving steady-state incompressible flows on block-structured grids
Yiye Zou, Tianyu Li, Lin Lu +4
Advances in deep learning have enabled physics-informed neural networks to solve partial differential equations. Numerical differentiation using the finite-difference (FD) method i…
Exploring the Robustness of Decentralized Training for Large Language Models
Lin Lu, Chenxi Dai, Wangcheng Tao +3
Decentralized training of large language models has emerged as an effective way to democratize this technology. However, the potential threats associated with this approach have no…
Prediction on Elastic Properties of Nb-doped Ni Systems
Jia Song, Zhibin Gao, Liang Zhang +3
On the basis of the first principles simulation, the structure, formation enthalpy, and mechanical properties (elastic constant, bulk, and shear modulus and hardness) of five Nb-do…
Evaluating an evidence-guided reinforcement learning framework in aligning light-parameter large language models with decision-making cognition in psychiatric clinical reasoning
Xinxin Lin, Guangxin Dai, Yi Zhong +20
Large language models (LLMs) hold transformative potential for medical decision support yet their application in psychiatry remains constrained by hallucinations and superficial re…
Simulated patient systems powered by large language model-based AI agents offer potential for transforming medical education
Huizi Yu, Jiayan Zhou, Lingyao Li +22
Background: Simulated patient systems are important in medical education and research, providing safe, integrative training environments and supporting clinical decision making. Ad…
Transfer Learning from One Cancer to Another via Deep Learning Domain Adaptation
Justin Cheung, Samuel Savine, Calvin Nguyen +2
Supervised deep learning models often achieve excellent performance within their training distribution but struggle to generalize beyond it. In cancer histopathology, for example,…
AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens
Lin Lu, Hai Yan, Zenghui Yuan +4
Jailbreak attacks in large language models (LLMs) entail inducing the models to generate content that breaches ethical and legal norm through the use of malicious prompts, posing a…
Feedback-Enhanced Online Multiple Testing with Applications to Conformal Selection
Lin Lu, Yuyang Huo, Haojie Ren +2
This work studies online multiple testing with feedback, where decisions are made sequentially, and the true state of the hypothesis is revealed after decisions are made, either in…
Flow Field Reconstruction via Voronoi-Enhanced Physics-Informed Neural Networks with End-to-End Sensor Placement Optimization
Renjie Xiao, Bingteng Sun, Yiling Chen +3
(short version abstract, full in article)High-fidelity flow field reconstruction is important in fluid dynamics, but it is challenged by sparse and spatiotemporally incomplete sens…
PH-Net: Parallelepiped Microstructure Homogenization via 3D Convolutional Neural Networks
Hao Peng, An Liu, Jingcheng Huang +3
Microstructures are attracting academic and industrial interests with the rapid development of additive manufacturing. The numerical homogenization method has been well studied for…
Learning Gradient Fields for Scalable and Generalizable Irregular Packing
Tianyang Xue, Mingdong Wu, Lin Lu +3
The packing problem, also known as cutting or nesting, has diverse applications in logistics, manufacturing, layout design, and atlas generation. It involves arranging irregularly…
Automated deep reinforcement learning for real-time scheduling strategy of multi-energy system integrated with post-carbon and direct-air carbon captured system
Tobi Michael Alabi, Nathan P. Lawrence, Lin Lu +2
The carbon-capturing process with the aid of CO2 removal technology (CDRT) has been recognised as an alternative and a prominent approach to deep decarbonisation. However, the main…
VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
Tri Cao, Bennett Lim, Yue Liu +7
Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access…