Zobrazeno 1 - 10
of 17 973
pro vyhledávání: '"yu, Lei"'
We propose a novel framework, Stable Diffusion-based Momentum Integrated Adversarial Examples (SD-MIAE), for generating adversarial examples that can effectively mislead neural network classifiers while maintaining visual imperceptibility and preserv
Externí odkaz:
http://arxiv.org/abs/2410.13122
Autor:
Yu, Lei, Tsering-xiao, Basang
The purpose of this paper is to establish a complete Schauder theory for the second-order linear elliptic equation and the time-harmonic Maxwell's system. We prove global H\"older regularity for the solutions to the time-harmonic anisotropic Maxwell'
Externí odkaz:
http://arxiv.org/abs/2410.10462
Autor:
Yu, Lei
Given a convex function $\Phi:[0,1]\to\mathbb{R}$, the $\Phi$-stability of a Boolean function $f$ is $\mathbb{E}[\Phi(T_{\rho}f(\mathbf{X}))]$, where $\mathbf{X}$ is a random vector uniformly distributed on the discrete cube $\{\pm1\}^{n}$ and $T_{\r
Externí odkaz:
http://arxiv.org/abs/2410.10147
Channel simulation is to simulate a noisy channel using noiseless channels with unlimited shared randomness. This can be interpreted as the reverse problem to Shannon's noisy coding theorem. In contrast to previous works, our approach employs R\'enyi
Externí odkaz:
http://arxiv.org/abs/2410.07984
Compositionality, the notion that the meaning of an expression is constructed from the meaning of its parts and syntactic rules, permits the infinite productivity of human language. For the first time, artificial language models (LMs) are able to mat
Externí odkaz:
http://arxiv.org/abs/2410.01444
Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful responses. Defending against such attacks remains challenging due to the opacity of jailbreaking mechanisms and the high computational cost of training LLMs ro
Externí odkaz:
http://arxiv.org/abs/2409.20089
Autor:
Cheng, Kun, Yu, Lei, Tu, Zhijun, He, Xiao, Chen, Liyu, Guo, Yong, Zhu, Mingrui, Wang, Nannan, Gao, Xinbo, Hu, Jie
Recent advances indicate that diffusion models hold great promise in image super-resolution. While the latest methods are primarily based on latent diffusion models with convolutional neural networks, there are few attempts to explore transformers, w
Externí odkaz:
http://arxiv.org/abs/2409.19589
Publikováno v:
Proceedings of the 35th International Conference on Scientific and Statistical Database Management (SSDBM 2023)
Protecting sensitive information in diagnostic data such as logs, is a critical concern in the industrial software diagnosis and debugging process. While there are many tools developed to automatically redact the logs for identifying and removing sen
Externí odkaz:
http://arxiv.org/abs/2409.17535
The curvature of ODE trajectories in diffusion models hinders their ability to generate high-quality images in a few number of function evaluations (NFE). In this paper, we propose a novel and effective approach to reduce trajectory curvature by util
Externí odkaz:
http://arxiv.org/abs/2409.17487
Video-based physiology, exemplified by remote photoplethysmography (rPPG), extracts physiological signals such as pulse and respiration by analyzing subtle changes in video recordings. This non-contact, real-time monitoring method holds great potenti
Externí odkaz:
http://arxiv.org/abs/2409.09366