Audio DeepFakes allow the creation of high-quality, convincing utterances and therefore pose a threat due to its potential applications such as impersonation or fake news. Methods for detecting these manipulations should be characterized by good generalization and stability leading to robustness against attacks conducted with techniques that are not explicitly included in the training. In this work, we introduce Attack Agnostic Dataset - a combination of two audio DeepFakes and one anti-spoofing datasets that, thanks to the disjoint use of attacks, can lead to better generalization of detection methods. We present a thorough analysis of current DeepFake detection methods and consider different audio features (front-ends). In addition, we propose a model based on LCNN with LFCC and mel-spectrogram front-end, which not only is characterized by a good generalization and stability results but also shows improvement over LFCC-based mode - we decrease standard deviation on all folds and EER in two folds by up to 5%.

Audio DeepFakes are utterances generated with the use of deep neural networks. They are highly misleading and pose a threat due to use in fake news, impersonation, or extortion. In this work, we focus on increasing accessibility to the audio DeepFake detection methods by providing SpecRNet, a neural network architecture characterized by a quick inference time and low computational requirements. Our benchmark shows that SpecRNet, requiring up to about 40% less time to process an audio sample, provides performance comparable to LCNN architecture — one of the best audio DeepFake detection models. Such a method can not only be used by online multimedia services to verify a large bulk of content uploaded daily but also, thanks to its low requirements, by average citizens to evaluate materials on their devices. In addition, we provide benchmarks in three unique settings that confirm the correctness of our model. They reflect scenarios of low–resource datasets, detection on short utterances and limited attacks benchmark in which we take a closer look at the influence of particular attacks on given architectures.

Removing noise from scanned pages is a vital step before their submission to optical character recognition (OCR) system. Most available image denoising methods are supervised where the pairs of noisy/clean pages are required. However, this assumption is rarely met in real settings. Besides, there is no single model that can remove various noise types from documents. Here, we propose a unified end-to-end unsupervised deep learning model, for the first time, that can effectively remove multiple types of noise, including salt & pepper noise, blurred and/or faded text, as well as watermarks from documents at various levels of intensity. We demonstrate that the proposed model significantly improves the quality of scanned images and the OCR of the pages on several test datasets.

Watermarking is an operation of embedding information into an image in a way that allows to identify ownership of the image despite applying some distortions on it. In this paper, we present a novel end-to-end solution for embedding and recovering the watermark in the digital image using convolutional neural networks. We propose a spreading method of the message over the spatial domain of the image, hence reducing the local bits per pixel capacity and significantly increasing robustness. To obtain the model we use adversarial training, apply noiser layers between the encoder and the decoder, and implement a precise JPEG approximation. Moreover, we broaden the spectrum of typically considered attacks on the watermark and we achieve high overall robustness, most notably against JPEG compression, Gaussian blur, subsampling or resizing. We show that an application of some attacks could increase robustness against other non-seen during training distortions across one group of attacks - a proper grouping of the attacks according to their scope allows to achieve high general robustness.