In the realm of digital media, the advent of AI-generated synthetic images has introduced significant challenges in distinguishing between real and fabricated visual content. These images, often indistinguishable from authentic ones, pose a threat to the credibility of digital media, with potential implications for disinformation and fraud. Our research addresses this challenge by employing machine learning techniques to discern between AI-generated and genuine images. Central to our approach is the CIFAKE dataset, a comprehensive collection of images labeled as "Real" and "Fake". We refine and adapt advanced deep learning architectures like ResNet, VGGNet, and DenseNet, utilizing transfer learning to enhance their precision in identifying synthetic images. We also compare these with a baseline model comprising a vanilla Support Vector Machine (SVM) and a custom Convolutional Neural Network (CNN). The experimental results were significant, demonstrating that our optimized deep learning models outperform traditional methods, with DenseNet achieving an accuracy of 97.74%. Our application study contributes by applying and optimizing these advanced models for synthetic image detection, conducting a comparative analysis using various metrics, and demonstrating their superior capability in identifying AI-generated images over traditional machine learning techniques. This research not only advances the field of digital media integrity but also sets a foundation for future explorations into the ethical and technical dimensions of AI-generated content in digital media.
Learning from SAM: Harnessing a Foundation Model for Sim2Real Adaptation by Regularization
Autonomous Intelligent Systems, University of Bonn, Germany(博恩大学自主智能系统);Lamarr Institute for Machine Learning and AI, Germany(机器学习与人工智能拉马尔研究所);Center for Robotics, University of Bonn, Germany(机器人中心)
Harnessing the Power of Large Vision Language Models for Synthetic Image Detection
Univ. Polytechnique Hauts-de-France(上法兰西理工大学);Technology Innovation Institute(技术创新研究院);Sorbonne Center for Artificial Intelligence(索邦人工智能中心);Sorbonne University Abu Dhabi(阿布扎比索邦大学)
Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN
College of Science and Engineering, University of Galway(戈尔韦大学科学与工程学院);School of Computer Science, University of Galway(戈尔韦大学计算机科学学院);Trinity College Dublin, the University of Dublin(都柏林大学圣三一学院);St James’s Hospital(圣詹姆斯医院)
本文提出 Derm-T2IM,用调优的 Stable Diffusion 生成多样化皮肤镜病变图像,并验证其可增强 CNN 与 ViT 在两个真实数据集上的分类鲁棒性和泛化性。
IntrinsicReal: Adapting IntrinsicAnything from Synthetic to Real Objects
The Hong Kong Polytechnic University(香港理工大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Cardiff University(卡迪夫大学);NanJing XiaoZhuang University(南京小庄大学)
Macau University of Science and Technology(澳门科技大学);Communication University of Zhejiang(浙江传媒学院);Zhejiang Lab(之江实验室);Communication University of China(中国传媒大学);Zhejiang University(浙江大学);Zhejiang Institute of Economics and Trade(浙江经贸职业技术学院)
Between Generating Noise and Generating Images: Noise in the Correct Frequency Improves the Quality of Synthetic Histopathology Images for Digital Pathology
Technion - IIT(以色列理工学院);Rambam Health Care Campus(兰巴姆医疗中心)
Randomize to Generalize: Domain Randomization for Runway FOD Detection
College of Aeronautical Engineering, National University of Sciences and Technology(国家科学技术大学航空工程学院);Khalifa University of Science and Technology(哈利法科学技术大学);Mohamed Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)