As deep learning inference is increasingly deployed in shared and cloud-based settings, a growing concern is input repurposing, in which data submitted for one task is reused by unauthorized models for another. Existing privacy defenses largely focus on restricting data access, but provide limited control over what downstream uses a released representation can still support. We propose a feature extraction framework that suppresses cross-model transfer while preserving accuracy for a designated classifier. The framework employs a variational latent bottleneck, trained with a task-driven cross-entropy objective and KL regularization, but without any pixel-level reconstruction loss, to encode inputs into a compact latent space. A dynamic binary mask, computed from per-dimension KL divergence and gradient-based saliency with respect to the frozen target model, suppresses latent dimensions that are uninformative for the intended task. Because saliency computation requires gradient access, the encoder is trained in a white-box setting, whereas inference requires only a forward pass through the frozen target model. On CIFAR-100, the processed representations retain strong utility for the designated classifier while reducing the accuracy of all unintended classifiers to below 2%, yielding a suppression ratio exceeding 45 times relative to unintended models. Preliminary experiments on CIFAR-10, Tiny ImageNet, and Pascal VOC provide exploratory evidence that the approach extends across task settings, although further evaluation is needed to assess robustness against adaptive adversaries.
VEDAL: Variational Error-Driven Asynchronous Learning for 3D Gaussian Splatting Pruning
Guangdong University of Technology(广东工业大学);Huizhou Boluo Power Supply Bureau, Guangdong Power Grid Co., Ltd.(惠州市博罗供电局,广东电网有限责任公司);Shenzhen Polytechnic University(深圳职业技术大学);School of Computer Science and Engineering, Huizhou University(惠州市大学计算机科学与工程学院)
提出VEDAL框架,通过变分自由能最小化、预测误差门控机制和变分不确定性头实现3D高斯泼溅的高效剪枝,在5.2倍压缩下仅损失0.31 dB PSNR。
Compact Latent Representation for Image Compression (CLRIC)
Fraunhofer Institute for Integrated Circuits IIS(弗劳恩霍夫集成电路研究所);Department of Physics, Faculty of Science, Sohag University(科学学院物理系,索哈格大学);Friedrich-Alexander University at Erlangen-Nürnberg(埃尔兰根-纽伦堡弗里德里希-亚历山大大学)
本文提出 CLRIC,利用预训练模型潜在变量和过拟合可学习函数实现任意质量级别的感知图像压缩,兼具低复杂度、模型与分辨率无关性及接近 SOTA 的质量。
D-CNN and VQ-VAE Autoencoders for Compression and Denoising of Industrial X-ray Computed Tomography Images
Department for X-Ray Imaging, Federal Institute for Materials Research(X射线成像部门,材料研究与测试联邦机构);Institute of Physics and Astronomy, University of Potsdam(物理与天文学研究所,波茨坦大学)