Recent studies have shown that deep convolutional neural networks (DCNN) are vulnerable to adversarial examples and sensitive to perceptual quality as well as the acquisition condition of images. These findings raise a big concern for the adoption of DCNN-based applications for critical tasks. In the literature, various defense strategies have been introduced to increase the robustness of DCNN, including re-training an entire model with benign noise injection, adversarial examples, or adding extra layers. In this paper, we investigate the connection between adversarial manipulation and image quality, subsequently propose a protective mechanism that doesnt require re-training a DCNN. Our method combines image quality assessment with knowledge distillation to detect input images that would trigger a DCCN to produce egregiously wrong results. Using the ResNet model trained on ImageNet as an example, we demonstrate that the detector can effectively identify poor quality and adversarial images.
A new embedding quality assessment method for manifold learning
National Disaster Reduction Center of China（国家减灾中心）；Tsinghua University（清华大学）；Institute of Applied Mathematics, AMSS, Chinese Academy of Sciences（中国科学院数学与系统科学研究院应用数学研究所）
Online Assessment Misconduct Detection using Internet Protocol and Behavioural Classification
Computational Science Research Center Korea Institute of Science and Technology（韩国科学技术院计算科学研究中心）；Pierson College PyeongTaek University（平泽大学皮尔逊学院）；Dow Centre The University of Queensland（昆士兰大学道中心）
Image quality assessment for closed-loop computer-assisted lung ultrasound
University College London（伦敦大学学院）；Frimley Park Hospital, Frimley Health NHS Foundation Trust（弗林利公园医院，弗林利健康NHS基金会信托）；Royal Berkshire Hospital, Royal Berkshire NHS Foundation Trust（皇家伯克郡医院，皇家伯克郡NHS基金会信托）；UCL Queen Square Institute of Neurology（伦敦大学学院皇后广场神经病学研究所）；University of Pavia（帕维亚大学）
Attention Down-Sampling Transformer, Relative Ranking and Self-Consistency for Blind Image Quality Assessment
King Fahd University of Petroleum and Minerals（法赫德国王石油与矿业大学）；SDAIA-KFUPM Joint Research Center for Artificial Intelligence（沙特数据与人工智能局-法赫德国王石油与矿业大学人工智能联合研究中心）
