Related papers: Sample-Specific Noise Injection For Diffusion-Base…
Deep learning models have been widely used in commercial acoustic systems in recent years. However, adversarial audio examples can cause abnormal behaviors for those acoustic systems, while being hard for humans to perceive. Various…
In this paper, we present PGDI, a diffusion-based speech inpainting framework for restoring missing or severely corrupted speech segments. Unlike previous methods that struggle with speaker variability or long gap lengths, PGDI can…
In this paper, we address the problem of single-microphone speech separation in the presence of ambient noise. We propose a generative unsupervised technique that directly models both clean speech and structured noise components, training…
Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to perturbations poses a significant threat to their reliability in real-world applications. Despite often being…
Score diffusion methods can learn probability densities from samples. The score of the noise-corrupted density is estimated using a deep neural network, which is then used to iteratively transport a Gaussian white noise density to a target…
Conditional diffusion models have demonstrated impressive performance in image manipulation tasks. The general pipeline involves adding noise to the image and then denoising it. However, this method faces a trade-off problem: adding too…
Single-channel audio separation aims to separate individual sources from a single-channel mixture. Most existing methods rely on supervised learning with synthetically generated paired data. However, obtaining high-quality paired data in…
Deep neural networks trained with Empirical Risk Minimization (ERM) perform well when both training and test data come from the same domain, but they often fail to generalize to out-of-distribution samples. In image classification, these…
Label noise is ubiquitous in real-world scenarios, posing a practical challenge to supervised models due to its effect in hurting the generalization performance of deep neural networks. Existing methods primarily employ the sample selection…
We propose a diffractive neural network with strong robustness based on Weight Noise Injection training, which achieves accurate and fast optical-based classification while diffraction layers have a certain amount of surface shape error. To…
Recently, many studies have demonstrated deep neural network (DNN) classifiers can be fooled by the adversarial example, which is crafted via introducing some perturbations into an original sample. Accordingly, some powerful defense…
We discover that common diffusion noise schedules do not enforce the last timestep to have zero signal-to-noise ratio (SNR), and some implementations of diffusion samplers do not start from the last timestep. Such designs are flawed and do…
Recommender systems often grapple with noisy implicit feedback. Most studies alleviate the noise issues from data cleaning perspective such as data resampling and reweighting, but they are constrained by heuristic assumptions. Another…
Despite the proliferation of generative models, achieving fast sampling during inference without compromising sample diversity and quality remains challenging. Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver…
Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…
Deep speaker embedding has demonstrated state-of-the-art performance in speaker recognition tasks. However, one potential issue with this approach is that the speaker vectors derived from deep embedding models tend to be non-Gaussian for…
Deep neural networks (DNNs) are vulnerable to adversarial perturbation, where an imperceptible perturbation is added to the image that can fool the DNNs. Diffusion-based adversarial purification focuses on using the diffusion model to…
Score-based diffusion models generate new samples by learning the score function associated with a diffusion process. While the effectiveness of these models can be theoretically explained using differential equations related to the…
Denoising in the sRGB image space is challenging due to large noise variability. Although end-to-end methods perform well, their effectiveness in real-world scenarios is limited by the scarcity of real noisy-clean image pairs, which are…
Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models. While they can be easily generated using gradient-based techniques in digital and physical…