Search Results for author: Minghui Li

Found 27 papers, 12 papers with code

Uncertainty-Aware Metabolic Stability Prediction with Dual-View Contrastive Learning

no code implementations1 Jun 2025 Peijin Guo, Minghui Li, Hewen Pan, Bowen Chen, Yang Wu, Zikang Guo, Leo Yu Zhang, Shengshan Hu, Shengqing Hu

Despite recent advances in graph neural networks (GNNs) for MS prediction, current approaches face two critical limitations: (1) incomplete molecular modeling due to atom-centric message-passing mechanisms that disregard bond-level topological features, and (2) prediction frameworks that lack reliable uncertainty quantification.

Contrastive Learning Prediction +1

Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets

no code implementations16 Apr 2025 Yechao Zhang, Yuxuan Zhou, Tianyu Li, Minghui Li, Shengshan Hu, Wei Luo, Leo Yu Zhang

Transfer learning from pre-trained encoders has become essential in modern machine learning, enabling efficient model adaptation across diverse tasks.

Transfer Learning

Multi-Modality Representation Learning for Antibody-Antigen Interactions Prediction

1 code implementation22 Mar 2025 Peijin Guo, Minghui Li, Hewen Pan, Ruixiang Huang, Lulu Xue, Shengqing Hu, Zikang Guo, Wei Wan, Shengshan Hu

While deep learning models play a crucial role in predicting antibody-antigen interactions (AAI), the scarcity of publicly available sequence-structure pairings constrains their generalization.

Graph Attention Prediction +1

Test-Time Backdoor Detection for Object Detection Models

no code implementations CVPR 2025 Hangtao Zhang, Yichen Wang, Shihui Yan, Chenyu Zhu, Ziqi Zhou, Linshan Hou, Shengshan Hu, Minghui Li, Yanjun Zhang, Leo Yu Zhang

To this end, we design TRAnsformation Consistency Evaluation (TRACE), a brand-new method for detecting poisoned samples at test time in object detection.

image-classification Image Classification +3

ViDTA: Enhanced Drug-Target Affinity Prediction via Virtual Graph Nodes and Attention-based Feature Fusion

no code implementations27 Dec 2024 Minghui Li, Zikang Guo, Yang Wu, Peijin Guo, Yao Shi, Shengshan Hu, Wei Wan, Shengqing Hu

By incorporating virtual graph nodes, we seamlessly integrate local and global features of drug molecular structures, expanding the GNN's receptive field.

Drug Discovery Graph Neural Network

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

1 code implementation22 Dec 2024 Yichen Wang, Yuxuan Chou, Ziqi Zhou, Hangtao Zhang, Wei Wan, Shengshan Hu, Minghui Li

In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations.

Disentanglement

PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation

no code implementations21 Dec 2024 Yufei Song, Ziqi Zhou, Minghui Li, Xianlong Wang, Hangtao Zhang, Menghao Deng, Wei Wan, Shengshan Hu, Leo Yu Zhang

With the rapid advancement of deep learning, the model robustness has become a significant research hotspot, \ie, adversarial attacks on deep neural networks.

Adversarial Attack image-classification +4

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need

1 code implementation4 Oct 2024 Xianlong Wang, Minghui Li, Wei Liu, Hangtao Zhang, Shengshan Hu, Yechao Zhang, Ziqi Zhou, Hai Jin

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data.

All

DarkSAM: Fooling Segment Anything Model to Segment Nothing

1 code implementation26 Sep 2024 Ziqi Zhou, Yufei Song, Minghui Li, Shengshan Hu, Xianlong Wang, Leo Yu Zhang, Dezhong Yao, Hai Jin

In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM.

model

Transferable Adversarial Facial Images for Privacy Protection

no code implementations18 Jul 2024 Minghui Li, Jiangxiong Wang, Hao Zhang, Ziqi Zhou, Shengshan Hu, Xiaobing Pei

To achieve this goal, we first exploit global adversarial latent search to traverse the latent space of the generative model, thereby creating natural adversarial face images with high transferability.

Face Recognition

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

1 code implementation16 Mar 2024 Ziqi Zhou, Minghui Li, Wei Liu, Shengshan Hu, Yechao Zhang, Wei Wan, Lulu Xue, Leo Yu Zhang, Dezhong Yao, Hai Jin

In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models.

Self-Supervised Learning

MISA: Unveiling the Vulnerabilities in Split Federated Learning

no code implementations18 Dec 2023 Wei Wan, Yuxuan Ning, Shengshan Hu, Lulu Xue, Minghui Li, Leo Yu Zhang, Hai Jin

This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks.

Edge-computing Federated Learning

Detecting and Corrupting Convolution-based Unlearnable Examples

1 code implementation30 Nov 2023 Minghui Li, Xianlong Wang, Zhifei Yu, Shengshan Hu, Ziqi Zhou, Longling Zhang, Leo Yu Zhang

To evaluate the generalization of our proposed COIN, we newly design two convolution-based UEs called VUDA and HUDA to expand the scope of convolution-based UEs.

AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning

1 code implementation14 Aug 2023 Ziqi Zhou, Shengshan Hu, Minghui Li, Hangtao Zhang, Yechao Zhang, Hai Jin

In this work, we propose AdvCLIP, the first attack framework for generating downstream-agnostic adversarial examples based on cross-modal pre-trained encoders.

Contrastive Learning Generative Adversarial Network +4

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

1 code implementation15 Jul 2023 Yechao Zhang, Shengshan Hu, Leo Yu Zhang, Junyu Shi, Minghui Li, Xiaogeng Liu, Wei Wan, Hai Jin

Building on these insights, we explore the impacts of data augmentation and gradient regularization on transferability and identify that the trade-off generally exists in the various training mechanisms, thus building a comprehensive blueprint for the regulation mechanism behind transferability.

Attribute Data Augmentation

Streamlining Social Media Information Retrieval for COVID-19 Research with Deep Learning

2 code implementations28 Jun 2023 Yining Hua, Jiageng Wu, Shixu Lin, Minghui Li, Yujie Zhang, Dinah Foer, Siwen Wang, Peilin Zhou, Jie Yang, Li Zhou

Conclusions: This study advances public health research by implementing a novel, systematic pipeline for curating symptom lexicons from social media data.

Information Retrieval named-entity-recognition +3

RIS-Position and Orientation Estimation in MIMO-OFDM Systems with Practical Scatterers

no code implementations9 Feb 2023 Sheng Hong, Minghui Li, Cunhua Pan, Marco Di Renzo, Wei zhang, Lajos Hanzo

A two-step positioning scheme is exploited, where the channel parameters are first acquired, and the position-related parameters are then estimated.

compressed sensing Position

PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples

no code implementations22 Nov 2022 Shengshan Hu, Junwei Zhang, Wei Liu, Junhui Hou, Minghui Li, Leo Yu Zhang, Hai Jin, Lichao Sun

In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes.

Adversarial Attack Point Cloud Classification +2

Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer

1 code implementation CVPR 2022 Shengshan Hu, Xiaogeng Liu, Yechao Zhang, Minghui Li, Leo Yu Zhang, Hai Jin, Libing Wu

While deep face recognition (FR) systems have shown amazing performance in identification and verification, they also arouse privacy concerns for their excessive surveillance on users, especially for public face images widely spread on social networks.

Face Recognition

Optimizing Privacy-Preserving Outsourced Convolutional Neural Network Predictions

no code implementations22 Feb 2020 Minghui Li, Sherman S. M. Chow, Shengshan Hu, Yuejing Yan, Chao Shen, Qian Wang

This paper proposes a new scheme for privacy-preserving neural network prediction in the outsourced setting, i. e., the server cannot learn the query, (intermediate) results, and the model.

Medical Image Analysis Prediction +2

LARSEN-ELM: Selective Ensemble of Extreme Learning Machines using LARS for Blended Data

no code implementations9 Aug 2014 Bo Han, Bo He, Rui Nian, Mengmeng Ma, Shujing Zhang, Minghui Li, Amaury Lendasse

Extreme learning machine (ELM) as a neural network algorithm has shown its good performance, such as fast speed, simple structure etc, but also, weak robustness is an unavoidable defect in original ELM for blended data.

Cannot find the paper you are looking for? You can Submit a new open access paper.