arXiv subjects

Yuheng Li

Publications and source records attributed to Yuheng Li.

76 records · Page 5Linked to original sources

arXiv2022

H$_2$O and CO$_2$ Surface Contamination of the Lithium-Stuffed Garnet

Understanding the reactivity of ubiquitous molecules on complex oxides has broad impacts in energy applications and catalysis. The garnet-type Li$_7$La$_3$Zr$_2$O$_{12}$ is a promising solid-state electrolyte for lithium(Li)-ion batteries, and it readily reacts with H$_2$O and CO$_2$ when exposed to ambient air. Such reactions form a contamination layer on Li$_7$La$_3$Zr$_2$O$_{12}$ that is detrimental to the battery operations. The strong interactions of Li$_7$La$_3$Zr$_2$O$_{12}$ with H$_2$O and CO$_2$, however, make Li$_7$La$_3$Zr$_2$O$_{12}$ a promising support to catalyze H$_2$O dissociation and CO$_2$ adsorption. Here, using first-principles calculations, we investigate the adsorption and reactions of H$_2$O and CO$_2$ on a Li$_7$La$_3$Zr$_2$O$_{12}$ surface. We show that H$_2$O reacts through the exchange of proton and Li$^{+}$ and produces metal hydroxide species. At high H$_2$O coverage, half of the H$_2$O molecules dissociate while the other half remain intact. CO$_2$ reacts with the Li$_7$La$_3$Zr$_2$O$_{12}$ surface directly to produce carbonate species. We clarify that the individual reactions of H$_2$O and CO$_2$ with Li$_7$La$_3$Zr$_2$O$_{12}$ are more thermodynamically favorable than the co-adsorption of H$_2$O and CO$_2$. Finally, we demonstrate that low temperature and high partial pressure promote the reactions of H$_2$O and CO$_2$ with Li$_7$La$_3$Zr$_2$O$_{12}$. For energy storage application of Li$_7$La$_3$Zr$_2$O$_{12}$, our study guides processing conditions to minimize surface contamination. From a catalysis point of view, our findings reveal the potential of using complex oxides, such as Li$_7$La$_3$Zr$_2$O$_{12}$ as a support for reactions requiring H$_2$O dissociation and strong CO$_2$ adsorption.

cond-mat.mtrl-sci↗

arXiv2021

CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes

Malicious applications of deepfakes (i.e., technologies generating target facial attributes or entire faces from facial images) have posed a huge threat to individuals' reputation and security. To mitigate these threats, recent studies have proposed adversarial watermarks to combat deepfake models, leading them to generate distorted outputs. Despite achieving impressive results, these adversarial watermarks have low image-level and model-level transferability, meaning that they can protect only one facial image from one specific deepfake model. To address these issues, we propose a novel solution that can generate a Cross-Model Universal Adversarial Watermark (CMUA-Watermark), protecting a large number of facial images from multiple deepfake models. Specifically, we begin by proposing a cross-model universal attack pipeline that attacks multiple deepfake models iteratively. Then, we design a two-level perturbation fusion strategy to alleviate the conflict between the adversarial watermarks generated by different facial images and models. Moreover, we address the key problem in cross-model optimization with a heuristic approach to automatically find the suitable attack step sizes for different models, further weakening the model-level conflict. Finally, we introduce a more reasonable and comprehensive evaluation method to fully test the proposed method and compare it with existing ones. Extensive experimental results demonstrate that the proposed CMUA-Watermark can effectively distort the fake facial images generated by multiple deepfake models while achieving a better performance than existing methods.

cs.CV↗

arXiv2021

Collaging Class-specific GANs for Semantic Image Synthesis

We propose a new approach for high resolution semantic image synthesis. It consists of one base image generator and multiple class-specific generators. The base generator generates high quality images based on a segmentation map. To further improve the quality of different objects, we create a bank of Generative Adversarial Networks (GANs) by separately training class-specific models. This has several benefits including -- dedicated weights for each class; centrally aligned data for each model; additional training data from other sources, potential of higher resolution and quality; and easy manipulation of a specific object in the scene. Experiments show that our approach can generate high quality images in high resolution while having flexibility of object-level control by using class-specific generators.

cs.CV↗

arXiv2020

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation

We present MixNMatch, a conditional generative model that learns to disentangle and encode background, object pose, shape, and texture from real images with minimal supervision, for mix-and-match image generation. We build upon FineGAN, an unconditional generative model, to learn the desired disentanglement and image generator, and leverage adversarial joint image-code distribution matching to learn the latent factor encoders. MixNMatch requires bounding boxes during training to model background, but requires no other supervision. Through extensive experiments, we demonstrate MixNMatch's ability to accurately disentangle, encode, and combine multiple factors for mix-and-match image generation, including sketch2color, cartoon2img, and img2gif applications. Our code/models/demo can be found at https://github.com/Yuheng-Li/MixNMatch

cs.CV↗