no code implementations • 6 Jun 2025 • Sheng Chen, Peiyu He, Jiaxin Hu, Ziyang Liu, Yansheng Wang, Tao Xu, Chongchong Zhang, Chao An, Shiyu Cai, Duo Cao, Kangping Chen, Shuai Chu, Tianwei Chu, Mingdi Dan, Min Du, Weiwei Fang, Pengyou Fu, Junkai Hu, Xiaowei Jiang, Zhaodi Jiang, Fuxuan Li, Jun Li, Minghui Li, Mingyao Li, Yanchang Li, Zhibin Li, Guangming Liu, Kairui Liu, Lihao Liu, Weizhi Liu, Xiaoshun Liu, Yufei Liu, Yunfei Liu, Qiang Lu, Yuanfei Luo, Xiang Lv, Hongying Ma, Sai Ma, Lingxian Mi, Sha Sa, Hongxiang Shu, Lei Tian, Chengzhi Wang, Jiayu Wang, Kaijie Wang, Qingyi Wang, Renwen Wang, Tao Wang, Wei Wang, Xirui Wang, Chao Wei, Xuguang Wei, Zijun Xia, Zhaohao Xiao, Tingshuai Yan, Liyan Yang, Yifan Yang, Zhikai Yang, Zhong Yin, Li Yuan, Liuchun Yuan, Chi Zhang, Jinyang Zhang, Junhui Zhang, Linge Zhang, Zhenyi Zhang, Zheyu Zhang, Dongjie Zhu, Hang Li, Yangang Zhang
The planning head utilizes flow matching and a novel masked ESDF loss to minimize collision risks for generating local trajectories, and the odometry head integrates multi-sensor inputs via a transformer encoder to predict the relative pose of the robot.
no code implementations • 1 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.
no code implementations • 16 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.
1 code implementation • 22 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.
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.
1 code implementation • 17 Mar 2025 • Yechao Zhang, Yingzhe Xu, Junyu Shi, Leo Yu Zhang, Shengshan Hu, Minghui Li, Yanjun Zhang
Deep neural networks (DNNs) are susceptible to universal adversarial perturbations (UAPs).
no code implementations • 27 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.
1 code implementation • 22 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.
no code implementations • 21 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.
no code implementations • 18 Nov 2024 • Xianlong Wang, Hewen Pan, Hangtao Zhang, Minghui Li, Shengshan Hu, Ziqi Zhou, Lulu Xue, Peijin Guo, Yichen Wang, Wei Wan, Aishan Liu, Leo Yu Zhang
To address this, we propose \textit{TrojanRobot}, a highly stealthy and broadly effective robotic backdoor attack in the physical world.
1 code implementation • 4 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.
1 code implementation • 26 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.
no code implementations • 18 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.
no code implementations • 16 Jul 2024 • Hangtao Zhang, Chenyu Zhu, Xianlong Wang, Ziqi Zhou, Changgan Yin, Minghui Li, Lulu Xue, Yichen Wang, Shengshan Hu, Aishan Liu, Peijin Guo, Leo Yu Zhang
Embodied AI represents systems where AI is integrated into physical entities.
1 code implementation • 16 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.
no code implementations • 18 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.
1 code implementation • 30 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.
1 code implementation • 14 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.
1 code implementation • 15 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.
2 code implementations • 28 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.
no code implementations • 17 May 2023 • Jiageng Wu, Xian Wu, Zhaopeng Qiu, Minghui Li, Yingying Zhang, Yefeng Zheng, Changzheng Yuan, Jie Yang
We systematically evaluate LLMs in the Chinese medical context and develop a novel in-context learning framework to enhance their performance.
1 code implementation • CVPR 2023 • Xiaogeng Liu, Minghui Li, Haoyu Wang, Shengshan Hu, Dengpan Ye, Hai Jin, Libing Wu, Chaowei Xiao
Deep neural networks are proven to be vulnerable to backdoor attacks.
no code implementations • 9 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.
no code implementations • 22 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.
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.
no code implementations • 22 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.
no code implementations • 9 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.