The success of image perturbations that are designed to fool image classifier is assessed in terms of both adversarial effect and visual imperceptibility. The conventional assumption on imperceptibility is that perturbations should strive for tight $L_p$-norm bounds in RGB space. In this work, we drop this assumption by pursuing an approach that exploits human color perception, and more specifically, minimizing perturbation size with respect to perceptual color distance. Our first approach, Perceptual Color distance C&W (PerC-C&W), extends the widely-used C&W approach and produces larger RGB perturbations. PerC-C&W is able to maintain adversarial strength, while contributing to imperceptibility. Our second approach, Perceptual Color distance Alternating Loss (PerC-AL), achieves the same outcome, but does so more efficiently by alternating between the classification loss and perceptual color difference when updating perturbations. Experimental evaluation shows PerC approaches outperform conventional $L_p$ approaches in terms of robustness and transferability, and also demonstrates that the PerC distance can provide added value on top of existing structure-based methods to creating image perturbations.
Imperceptible and Reversible Adversarial Examples against Vision-Language Models for Privacy Protection
School of Cyber Science and Engineering, Huazhong University of Science and Technology（华中科技大学网络空间安全学院）；College of Computer Science, Chongqing University（重庆大学计算机科学学院）；School of Software and engineering, Huazhong University of Science and Technology（华中科技大学软件工程学院）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）
PWAVEP: Purifying Imperceptible Adversarial Perturbations in 3D Point Clouds via Spectral Graph Wavelets
Software College, Northeastern University（东北大学软件学院）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；Software College, Shenyang University of Technology（沈阳理工大学软件学院）
SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generation
School of Future Technology, South China University of Technology（华南理工大学未来技术学院）；School of Computer Science and Engineering, South China University of Technology（华南理工大学计算机科学与工程学院）；School of Computer Science and Technology, Ocean University of China（中国海洋大学计算机科学与技术学院）；School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算与信息系统学院）
Eidos: Efficient, Imperceptible Adversarial 3D Point Clouds
Institute of Intelligent Software（智能软件研究所）；Universität des Saarlandes（萨尔大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；University of Liverpool（利物浦大学）；Purple Mountain Laboratories（紫金山实验室）；LIS, Centrale Méditerranée Marseille（马赛中央理工学院LIS实验室）
Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection
University of British Columbia（英属哥伦比亚大学）；Department of Statistics, University of British Columbia（英属哥伦比亚大学统计系）；Department of Electrical and Computer Engineering, University of British Columbia（英属哥伦比亚大学电气与计算机工程系）；School of Information and Communications Engineering, Xi’an Jiaotong University（西安交通大学信息与通信工程学院）
Imperceptible Adversarial Examples for Fake Image Detection
Chengdu University of Information Technology（成都信息工程大学）；Keya Medical（科亚医疗）；University at Buffalo, State University of New York（纽约州立大学布法罗分校）；Microsoft Research Asia（微软亚洲研究院）
Human-Imperceptible Physical Adversarial Attack for NIR Face Recognition Models
School of Computer Science and Technology, China University of Mining and Technology（中国矿业大学（北京）计算机科学与技术学院）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；Department of Engineering and Design, Technische Universität München（慕尼黑工业大学工程与设计系）
Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
Sun Yat-Sen University（中山大学）；Nanyang Technological University（南洋理工大学）；University of Oxford（牛津大学）；National University of Defense Technology（国防科技大学）；National University of Singapore（新加坡国立大学）；Chinese Academy of Sciences（中国科学院）
Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving
Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China（深圳先进研究院，电子科技大学）；School of Mechanical and Aerospace Engineering, Nanyang Technological University（南洋理工大学机械与航空航天工程学院）；School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China（电子科技大学机械与电气工程学院）
Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
Rensselaer Polytechnic Institute（伦斯勒理工学院）；University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）；Xian Jiaotong University（西安交通大学）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；West China Hospital（华西医院）
Visually Imperceptible Adversarial Patch Attacks on Digital Images
Zhejiang University of Science and Technology（浙江科技大学）；Hangzhou Hikvision Digital Technology Co., Ltd.（杭州海康威视数字技术股份有限公司）；University of Electronic Science and Technology of China（电子科技大学）；Guangzhou University（广州大学）；Zhejiang University（浙江大学）；CY Cergy Paris University（CY塞尔吉巴黎大学）
Harnessing Perceptual Adversarial Patches for Crowd Counting
Beihang University（北京航空航天大学）；Zhongguancun Laboratory（中关村实验室）；Johns Hopkins University（约翰斯·霍普金斯大学）；JD Explore Academy（京东探索研究院）；The University of Sydney（悉尼大学）
Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution
Northwestern University（西北大学）；Universidad de Granada（格拉纳达大学）
视频超分辨率（VSR）已成为视频处理中的关键问题之一。在深度学习文献中，最近的工作已经显示出使用基于对抗性和感知损失来提高各种图像复原任务的性能的好处;然而，这些还没有应用于视频超分辨率。在这项工作中，我们提出了一个生成对抗网络（GAN）为基础的制定VSR。我们引入了一个新的生成器网络优化的VSR问题，命名为VSRResNet，以及一个新的神经网络架构，以正确指导VSRResNet在GAN训练。我们进一步增强了我们的VSR GAN制定与两个正则化，在特征空间和像素空间的距离损失，以获得我们最终的VSRResistance GAN模型。我们表明，用均方误差损失预训练我们的生成器仅在数量上超过当前最先进的VSR模型。最后，我们采用PercepDist度量（Zhang et al.，2018）来比较最先进的VSR模型。我们表明，与常用的PSNR/SSIM指标相比，该指标更准确地评估从神经网络获得的SR解决方案的感知质量。最后，我们表明，我们提出的模型，VSRRescultGAN模型，优于目前最先进的SR模型，无论是定量和定性。
