IEEE Transactions on Pattern Analysis and Machine Intelligence最新文献_第3页

Evidence-based Multi-Feature Fusion for Adversarial Robustness. 基于证据的多特征融合对抗鲁棒性。

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-06-23 DOI: 10.1109/tpami.2025.3582518

Zheng Wang,Xing Xu,Lei Zhu,Yi Bin,Guoqing Wang,Yang Yang,Heng Tao Shen

{"title":"Evidence-based Multi-Feature Fusion for Adversarial Robustness.","authors":"Zheng Wang,Xing Xu,Lei Zhu,Yi Bin,Guoqing Wang,Yang Yang,Heng Tao Shen","doi":"10.1109/tpami.2025.3582518","DOIUrl":"https://doi.org/10.1109/tpami.2025.3582518","url":null,"abstract":"The accumulation of adversarial perturbations in the feature space makes it impossible for Deep Neural Networks (DNNs) to know what features are robust and reliable, and thus DNNs can be fooled by relying on a single contaminated feature. Numerous defense strategies attempt to improve their robustness by denoising, deactivating, or recalibrating non-robust features. Despite their effectiveness, we still argue that these methods are under-explored in terms of determining how trustworthy the features are. To address this issue, we propose a novel Evidence-based Multi-Feature Fusion (termed EMFF) for adversarial robustness. Specifically, our EMFF approach introduces evidential deep learning to help DNNs quantify the belief mass and uncertainty of the contaminated features. Subsequently, a novel multi-feature evidential fusion mechanism based on Dempster's rule is proposed to fuse the trusted features of multiple blocks within an architecture, which further helps DNNs avoid the induction of a single manipulated feature and thus improve their robustness. Comprehensive experiments confirm that compared with existing defense techniques, our novel EMFF method has obvious advantages and effectiveness in both scenarios of white-box and black-box attacks, and also prove that by integrating into several adversarial training strategies, we can improve the robustness of across distinct architectures, including traditional CNNs and recent vision Transformers with a few extra parameters and almost the same cost.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"269 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144370405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modeling. 基于三维建模的热图像中人检测器物理对抗实例。

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-06-23 DOI: 10.1109/tpami.2025.3582334

Xiaopei Zhu,Siyuan Huang,Zhanhao Hu,Jianmin Li,Jun Zhu,Xiaolin Hu

{"title":"Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modeling.","authors":"Xiaopei Zhu,Siyuan Huang,Zhanhao Hu,Jianmin Li,Jun Zhu,Xiaolin Hu","doi":"10.1109/tpami.2025.3582334","DOIUrl":"https://doi.org/10.1109/tpami.2025.3582334","url":null,"abstract":"Thermal Infrared detection is widely used in autonomous driving, medical AI, etc., but its security has only attracted attention recently. We propose infrared adversarial clothing designed to evade thermal person detectors in real-world scenarios. The design of the adversarial clothing is based on 3D modeling, which makes it easier to simulate multiangle scenes near the real world compared to 2D modeling. We optimized the black patch layout pattern of 3D clothing based on the adversarial example technique and made physical adversarial clothing using the aerogel. The idea is to paste a set of square aerogel patches, which display black squares in thermal images, in the inner side of clothing at specific locations with specific orientations. To enhance realism, we propose a method to build infrared 3D models with real infrared photos and develop texture maps for 3D models to simulate varied infrared characteristics over time and location. In physical attacks, we achieved an attack success rate of 80.11% indoors and 76.85% outdoors against YOLOv9. In contrast, randomly placed patches yielded much lower success rates (26.53% indoors and 23.03% outdoors). The adversarial clothing also showed good transferability to unknown detectors with an ensemble attack method, demonstrating the effectiveness of our approach.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"38 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144370406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Any Fashion Attribute Editing: Dataset and Pretrained Models 任何时尚属性编辑：数据集和预训练模型

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-06-20 DOI: 10.1109/tpami.2025.3581793

Shumin Zhu, Xingxing Zou, Wenhan Yang, Wai Keung Wong

引用次数: 0

FedID: Enhancing Federated Learning Security Through Dynamic Identification FedID：通过动态识别增强联邦学习的安全性

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-06-20 DOI: 10.1109/tpami.2025.3581555

Siquan Huang, Yijiang Li, Chong Chen, Ying Gao, Xiping Hu

引用次数: 0

Generalizing to New Dynamical Systems via Frequency Domain Adaptation 基于频域自适应的新动力系统推广

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-06-20 DOI: 10.1109/tpami.2025.3581941

Tiexin Qin, Hong Yan, Haoliang Li

引用次数: 0

Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack 高迁移性视觉语言攻击的语义对齐对抗进化三角

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-06-20 DOI: 10.1109/tpami.2025.3581476

Xiaojun Jia, Sensen Gao, Qing Guo, Simeng Qin, Ke Ma, Yihao Huang, Yang Liu, Ivor Tsang, Xiaochun Cao

引用次数: 0

PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes PanopticNeRF-360：全景3d到2d标签转移在城市场景

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-06-20 DOI: 10.1109/tpami.2025.3581608

Xiao Fu, Shangzhan Zhang, Tianrun Chen, Yichong Lu, Xiaowei Zhou, Andreas Geiger, Yiyi Liao

引用次数: 0

Social Reasoning-Aware Trajectory Prediction via Multimodal Language Model 基于多模态语言模型的社会推理感知轨迹预测

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-06-20 DOI: 10.1109/tpami.2025.3582000

Inhwan Bae, Junoh Lee, Hae-Gon Jeon

引用次数: 0

GUS-IR: Gaussian Splatting With Unified Shading for Inverse Rendering 高斯-红外：高斯喷溅与统一的底纹反演渲染

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-06-20 DOI: 10.1109/tpami.2025.3578416

Zhihao Liang, Hongdong Li, Kui Jia, Kailing Guo, Qi Zhang

引用次数: 0

Supervised Learning in Dynamic and Non Stationary Environments 动态和非静态环境下的监督学习

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-06-20 DOI: 10.1109/tpami.2025.3581982

Alberto Giaretta, Mauro Bisiacco, Gianluigi Pillonetto

引用次数: 0