检索结果-内蒙古大学图书馆

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Ziqi Li, Minghui Liu, Wei Hu, Shengshan Zhang, Yechao Wan, Wei Xue, Lulu Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab. China Cluster and Grid Computing Lab. China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. 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. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six

关键词： Topology

Robot Manipulator Control via Solving Four-Layered Time-Variant Equations Including Linear, Nonlinear Equalities and Inequalities 11

学校读者我要写书评

暂无评论

Robot Manipulator Control via Solving Four-Layered Time-Vari...

11th International Conference on Intelligent Control and information Processing, ICICIP 2021

作者： Zhu, Xinhui Zhang, Li Shi, Yang Wang, Jing Li, Jian Xinyang Normal University School of Computer and Information Technology Xinyang464000 China Henan Key Lab. of Analysis and Application of Education Big Data Xinyang Normal University Xinyang464000 China Yangzhou University School of Information Engineering Yangzhou225127 China

ISBN: (纸本)9781665425155

Robot manipulator control is a complicated multi-tasking problem in reality. It includes not only basic tracking task, but also additional tasks, such as conquering joint angle limits, posture control. However, most existing works only consider the goal of tracking and formulate it as single-layered time-variant problems, which leads to impracticality. In this work, robot manipulator control problem is formulated as four-layered time-variant equations including linear, nonlinear equalities and inequalities. Each layer formulates one subtask: The first layer of nonlinear equality describes basic tracking task based on forward kinematics;The second layer and third layer are inequalities, which describe joint angle upper and lower limits;The last layer is a linear equality with respect to joint angle velocity, which could be designed by user to describe other task, such as posture control. To solve this complicated four-layered time-variant problem, it is converted as single-layered equation based on the zeroing neural dynamics method. Then, continuous-time solution is proposed. Furthermore, discrete-time algorithm is proposed based on a third-order time-discretization formula and continuous-time solution. Numerical experiments illustrate the effectiveness and superiority compared to existing work. © 2021 IEEE.

关键词： Industrial robots

Downstream-agnostic Adversarial Examples

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

International Conference on computer Vision (ICCV)

作者： Ziqi Zhou Shengshan Hu Ruizhi Zhao Qian Wang Leo Yu Zhang Junhui Hou Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan University School of Information and Communication Technology Griffith University Department of Computer Science City University of Hong Kong School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial *** this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://***/CGCL-codes/AdvEncoder.

关键词：

Automatic combination strategy search in segmentation of Cardiac T1 mapping image 4

学校读者我要写书评

暂无评论

Automatic combination strategy search in segmentation of Car...

4th International Conference on Advanced Electronic Materials, computers and Software engineering, AEMCSE 2021

作者： Wangchen, Xingyu Shen, Wenfeng Takasumi, Hideaki Seino, Shinya Zhu, Xin Shanghai University School of Computer Engineering and Science Shanghai China Shanghai University School of Computer Engineering and Science Shanghai Institute for Advanced Communication and Data Science Shanghai China Fukushima Medical University Hospital Department of Radiology Fukushima Japan The University of Aizu Biomedical Information Engineering Lab Fukushima9658580 Japan

ISBN: (纸本)9781665415965

Fusion of multiple medical images may improve image quality and ease feature extraction for the diagnosis and therapy of diseases. In cardiac magnetic resonance (MR) images T1 mapping, multiple MR images are reconstructed for the estimation of T1 mapping;therefore, heart myocardium should be segmented from images for further analysis using T1 values. Traditionally, segmentation is performed for each image separately, and the per-image segmentation results are combined in a complicated way to get a final segmentation result. Traditional combination methods require the segmentation results of all images satisfy certain criteria, and therefore often fail because of low image quality. However, it is very difficult to design a combination strategy to integrate the information of multiple images for segmentation. In this study, we designed the Segfuse network based on convolutional neural networks to get strategies for improving the segmentation performance of T1 mapping images even when some images were of low quality. After validating with 112 images from 42 subjects, the segmentation accuracy based on the Segfuse had a mean dice of 80.2%, nearly equivalent to that of a traditional method. © 2021 IEEE.

关键词： Image segmentation

A Hybrid Model of Deep Learning Features and Clinical Features for Severe Cases Predication of COVID-19

学校读者我要写书评

暂无评论

A Hybrid Model of Deep Learning Features and Clinical Featur...

Medical Imaging 2023: computer-Aided Diagnosis

作者： Kitrungrotsakul, Titinunt Chen, Qingqing Wu, Huitao Srichola, Preeyanuch Hu, Hongjie Zhu, Wenchao Chen, Chao Xu, Fangyi Zhou, Yong Lin, Lanfen Tong, Ruofeng Li, Jingsong Chen, Yen-Wei Research Center for Healthcare Data Science Zhejiang Lab Hangzhou China Sir Run Run Shaw Hospital Zhejiang University School of Medicine Hangzhou China Intelligent Healthcare Team Baidu Inc. Beijing China Kasetsart Agricultural and Agro-Industrial Product Improvement Institute Kasetsart University Bangkok Thailand College of Computer Science and Technology Zhejiang University Hangzhou China Graduate School of Information Science and Engineering Ritsumeikan University Shiga Japan

ISBN: (纸本)9781510660359

COVID-19 has spread around the world since 2019. Approximately 6.5% of COVID-19 a risk of developing severe disease with high mortality rate. To reduce the mortality rate and provide appropriate treatment, this research established an integrated models with to predict the clinical outcome of COVID-19 patients with clinical, deep learning and radiomics features. To obtain the optimal feature combination for prediction, 9 clinical features combination was selected from all available clinical factors after using LASSO, 18 deep learning features from U-Net architecture, and 9 radiomics features from segmentation result. A total of 213 COVID-19 patients and 335 non-COVID-19 patients from 5 hospitals were enrolled and used as training and test sample in this research. The proposed model obtained an accuracy, precision, recall, specificity, F1-score and ROC curve of 0.971, 0.943, 0.937, 0.974, 0.941 and 0.979, respectively, which exceeds the related work using only clinical, deep learning or radiomics factors. © 2023 SPIE.

关键词： COVID-19

TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Shaoqing Li, Fang Huang, Peixiang Song, Ziying Yang, Zhi-Xin State Key Laboratory of Internet of Things for Smart City Department of Electromechanical Engineering University of Macau 999078 China School of Mechanical Engineering Beijing Institute of Technology China College of Engineering Peking University Beijing China School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China

Accurate multi-view 3D object detection is essential for applications such as autonomous driving. Researchers have consistently aimed to leverage LiDAR’s precise spatial information to enhance camera-based detectors through methods like depth supervision and bird-eye-view (BEV) feature distillation. However, existing approaches often face challenges due to the inherent differences between LiDAR and camera data representations. In this paper, we introduce the TiGDistill-BEV, a novel approach that effectively bridges this gap by leveraging the strengths of both sensors. Our method distills knowledge from diverse modalities(e.g., LiDAR) as the teacher model to a camera-based student detector, utilizing the Target Inner-Geometry learning scheme to enhance camera-based BEV detectors through both depth and BEV features by leveraging diverse modalities. Specially, we propose two key modules: an inner-depth supervision module to learn the low-level relative depth relations within objects which equips detectors with a deeper understanding of object-level spatial structures, and an inner-feature BEV distillation module to transfer high-level semantics of different keypoints within foreground targets. To further alleviate the domain gap, we incorporate both inter-channel and inter-keypoint distillation to model feature similarity. Extensive experiments on the nuScenes benchmark demonstrate that TiGDistill-BEV significantly boosts camera-based only detectors achieving a state-of-the-art with 62.8% NDS and surpassing previous methods by a significant margin. The codes is available at: https://***/Public-BOTs/*** Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

Secure Semantic Communications: Fundamentals and Challenges

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Zhaohui Chen, Mingzhe Li, Gaolei Yang, Yang Zhang, Zhaoyang The College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Hangzhou310007 China Zhejiang Lab Hangzhou31121 China The School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China The School of Information and Communication Engineering BUPT The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States

Semantic communication allows the receiver to know the intention instead of the bit information itself, which is an emerging technique to support real-time human-machine and machine-to-machine interactions for future wireless communications. In semantic communications, both transmitter and receiver share some common knowledge, which can be used to extract small-size information at the transmitter and recover the original information at the receiver. Due to different design purposes, security issues in semantic communications have two unique features compared to standard bit-wise communications. First, an attacker in semantic communications considers not only the amount of stolen data but also the meanings of stolen data. Second, an attacker in semantic communication systems can attack not only semantic information transmission as done in standard communication systems but also attacks machine learning (ML) models used for semantic information extraction since most of semantic information is generated using ML based methods. Due to these unique features, in this paper, we present an overview on the fundamentals and key challenges in the design of secure semantic communication. We first provide various methods to define and extract semantic information. Then, we focus on secure semantic communication techniques in two areas: information security and semantic ML model security. For each area, we identify the main problems and challenges. Then, we will provide a comprehensive treatment of these problems. In a nutshell, this article provides a holistic set of guidelines on how to design secure semantic communication systems over real-world wireless communication networks. © 2023, CC BY-SA.

关键词： Semantics

VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Song, Ziying Zhang, Guoxin Xie, Jun Liu, Lin Jia, Caiyan Xu, Shaoqing Wang, Zhepeng School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China Hebei University of Science and Technology School of Information Science and Engineering Shijiazhuang050018 China Lenovo Research Beijing100085 China State Key Laboratory of Internet of Things for Smart City Department of Electrome chanical Engineering University of Macau 999078 China

LiDAR-camera fusion can enhance the performance of 3D object detection by utilizing complementary information between depth-aware LiDAR points and semantically rich images. Existing voxel-based methods face significant challenges when fusing sparse voxel features with dense image features in a one-to-one manner, resulting in the loss of the advantages of images, including semantic and continuity information, leading to sub-optimal detection performance, especially at long distances. In this paper, we present VoxelNextFusion, a multi-modal 3D object detection framework specifically designed for voxel-based methods, which effectively bridges the gap between sparse point clouds and dense images. In particular, we propose a voxel-based image pipeline that involves projecting point clouds onto images to obtain both pixel- and patch-level features. These features are then fused using a self-attention to obtain a combined representation. Moreover, to address the issue of background features present in patches, we propose a feature importance module that effectively distinguishes between foreground and background features, thus minimizing the impact of the background features. Extensive experiments were conducted on the widely used KITTI and nuScenes 3D object detection benchmarks. Notably, our VoxelNextFusion achieved around +3.20% in AP@0.7 improvement for car detection in hard level compared to the Voxel R-CNN baseline on the KITTI test dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Object recognition

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Hangtao Hu, Shengshan Wang, Yichen Zhang, Leo Yu Zhou, Ziqi Wang, Xianlong Zhang, Yanjun Chen, Chao School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Cluster and Grid Computing Lab China School of Information and Communication Technology Griffith University Australia University of Technology Sydney Australia RMIT University Australia

Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: SPONGE for triggering widespread misidentifications and BLINDING for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement (∼10%-60% absolute and ∼2-7× relative) in attack efficacy over state-of-the-art attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Denial-of-service attack