Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Laszkiewicz, Mike"'
As speech generation technology advances, so do the potential threats of misusing spoofed speech signals. One way to address these threats is by attributing the signals to their source generative model. In this work, we are the first to tackle the si
Externí odkaz:
http://arxiv.org/abs/2411.14013
Recent advances in multimodal foundation models have set new standards in few-shot anomaly detection. This paper explores whether high-quality visual features alone are sufficient to rival existing state-of-the-art vision-language models. We affirm t
Externí odkaz:
http://arxiv.org/abs/2405.14529
Recent years have witnessed a rapid development of deep generative models for creating synthetic media, such as images and videos. While the practical applications of these models in everyday tasks are enticing, it is crucial to assess the inherent r
Externí odkaz:
http://arxiv.org/abs/2401.13555
In this work, we propose a set-membership inference attack for generative models using deep image watermarking techniques. In particular, we demonstrate how conditional sampling from a generative model can reveal the watermark that was injected into
Externí odkaz:
http://arxiv.org/abs/2307.15067
Recent breakthroughs in generative modeling have sparked interest in practical single-model attribution. Such methods predict whether a sample was generated by a specific generator or not, for instance, to prove intellectual property theft. However,
Externí odkaz:
http://arxiv.org/abs/2306.06210
Learning the tail behavior of a distribution is a notoriously difficult problem. By definition, the number of samples from the tail is small, and deep generative models, such as normalizing flows, tend to concentrate on learning the body of the distr
Externí odkaz:
http://arxiv.org/abs/2206.10311
Normalizing flows, which learn a distribution by transforming the data to samples from a Gaussian base distribution, have proven powerful density approximations. But their expressive power is limited by this choice of the base distribution. We, there
Externí odkaz:
http://arxiv.org/abs/2107.07352
Many Machine Learning algorithms are formulated as regularized optimization problems, but their performance hinges on a regularization parameter that needs to be calibrated to each application at hand. In this paper, we propose a general calibration
Externí odkaz:
http://arxiv.org/abs/2005.00466
Autor:
Laszkiewicz, Mike1 mlaszkiewicz@ra.rockwell.com
Publikováno v:
Plant Engineering. Sep2003, Vol. 57 Issue 9, p30. 3p.
Autor:
Laszkiewicz, Mike
Publikováno v:
Plant Engineering. Oct2002, Vol. 56 Issue 10, p30. 3p. 1 Color Photograph.