Abstract: A method for training a neural network.

Abstract: A computer-implemented system and method relate to certified defense against adversarial patch attacks. A set of one-mask images is generated using a first mask at a set of predetermined regions of a source image. The source image is obtained from a sensor. A set of one-mask predictions is generated, via a machine learning system, based on the set of one-mask images. A first one-mask image is extracted from the set of one-mask images. The first one-mask image is associated with a first one-mask prediction that is identified as a minority amongst the set of one-mask predictions. A set of two-mask images is generated by masking the first one-mask image using a set of second masks. The set of second masks include at least a first submask and a second submask in which a dimension of the first submask is less than a dimension of the first mask. A set of two-mask predictions is generated based on the set of two-mask images.

Abstract: A system and method include dividing a source image into a plurality of source regions, which are portions of the source image that correspond to a plurality of grid regions. A mask is used to create a first masked region that masks a first source region and a first unmasked region that comprises a second source region. A first inpainted region is generated by inpainting the first masked region based on the second source region. Similarity data is generated based on a similarity assessment. A protected image is generated that includes at least (i) the first masked region at a first grid region when the similarity data indicates that the first source region is not similar to the first inpainted region and (ii) the first inpainted region at the first grid region when the similarity data indicates that the first source region is similar to the first inpainted region.

Abstract: A computer-program product storing instructions which, when executed by a computer, cause the computer to receive an input data from a sensor, generate a training data set utilizing the input data, wherein the training data set is created by creating one or more copies of the input data and adding noise to the one or more copies, send the training data set to a diffusion model, wherein the diffusion model is configured to reconstruct and purify the training data set by removing noise associated with the input data and reconstructing the one or more copies of the training data set to create a modified input data set, send the modified input data set to a fixed classifier, and output a classification associated with the input data in response to a majority vote of the classification obtained by the fixed classifier of the modified input data set.

Abstract: A method for training a neural network for determining a task output with respect to a given task. The method includes: providing unlabeled and/or labelled encoder training records of measurement data; training the encoder network to map encoder training records to representations towards the goal that these representations, and/or or one or more work products derived from the representations, fulfil a self-consistency condition or correspond to ground truth; providing task training records that are labelled with ground truth; and training the association network and the task head networks towards the goal that, when a task training record is mapped to a representation using the encoder network, and the representation is mapped to a task output by the combination of the association network and the task head networks, the so-obtained task output corresponds to the ground truth with which the training record is labelled, as measured by a task loss function.

Abstract: A computer-implemented method for determining an adversarial patch for a machine learning system. The machine learning system is configured for image analysis and determines an output signal based on an input image. The output signal is determined based on an output of an attention layer of the machine learning system. The adversarial patch is determined by optimizing the adversarial patch with respect to a loss function, wherein the loss function comprises a term that characterizes a sum of attention weights of the attention layer with respect to a position of the adversarial patch in the input image and the method comprises a step of maximizing the term.

Abstract: A computer-implemented method for determining an output signal characterizing a semantic segmentation and/or an instance segmentation of an image. The method includes: determining a first intermediate output signal from a machine learning system, wherein the first intermediate output signal characterizes a semantic segmentation and/or an instance segmentation of the image; adapting parameters of the machine learning system based on a loss function, wherein the loss function characterizes an entropy or a cross-entropy of the first intermediate output signal; determining the output signal from the machine learning system based on the image and the adapted parameters.

Abstract: An image classifier for classifying an input image x with respect to combinations of an object value o and an attribute value. The image classifier includes an encoder network that is configured to map the input image to a representation comprising multiple independent components; an object classification head network configured to map representation components of the input image to one or more object values; an attribute classification head network configured to map representation components of the input image to one or more attribute values; and an association unit configured to provide, to each classification head network, a linear combination of those representation components of the input image x that are relevant for the classification task of the respective classification head network. A method for training the image classifier is also provided.

Abstract: A computer-implemented method for adapting a pretrained machine learning system, which has been trained on a first training data set, to a second dataset, wherein the second dataset has different characteristics than the first data set. An input transformation module for partly undoing the distribution shift between the first and second training data set is provided.

Abstract: A method for training a neural network.

Abstract: A computer-implemented method for determining an output signal for an input signal using a classifier. The output signal characterizes a classification of the input signal. The method includes: determining a latent representation based on the input signal using an invertible factorization model comprised in the classifier, the latent representation comprises a plurality of factors; determining the output signal based on the latent representation using an internal classifier comprised in the classifier.

Abstract: A computer-implemented method for training a classifier. The classifier is configured to determine an output signal characterizing a classification of an input signal. The training of the classifier includes: determining a first training input signal; determining a first latent representation comprising a plurality of factors based on the first training input signal by means of an invertible factorization model, wherein the invertible factorization model, determining a second latent representation by adapting at least one factor of the first latent representation; determining a second training input signal based on the second latent representation by means of the invertible factorization model; and training the classifier based on the second training input signal.

Abstract: A system and method are provided for classifying objects in spatial data using a machine learned model, as well as a system and method for training the machine learned model. The machine learned model may comprise a content sensitive classifier, a location sensitive classifier and at least one outlier detector. Both classifiers may jointly distinguish between objects in spatial data being in-distribution or marginal-out-of-distribution. The outlier detection part may be trained on inlier examples from the training data, while the presence of actual outliers in the input data of the machine learnable model may be mimicked in the feature space of the machine learnable model during training. The combination of these parts may provide a more robust classification of objects in spatial data with respect to outliers, without having to increase the size of the training data.

Abstract: A method for generating a universal data signal interference for generating a manipulated data signal for deceiving a first machine learning system, which is configured to ascertain a semantic segmentation of a received one-dimensional or multidimensional data signal, The method includes a) ascertaining a training data set that includes pairs of data signals and associated desired semantic segmentations, b) generating the data signal interference, as a function of the data signals of the training data set, of the associated desired semantic segmentation, as well as of estimated semantic segmentations of the data signals acted upon by the data signal interference.

Abstract: A method for generating a manipulated data signal for misleading a first machine learning system, which is designed to ascertain a semantic segmentation of a received one-dimensional or multi-dimensional data signal, the method having the following steps: a) ascertaining a desired semantic segmentation of the manipulated data signal; and b) generating the manipulated signal as a function of the received data signal and the ascertained desired semantic segmentation as well as an estimated semantic segmentation of the manipulated data signal.

Abstract: A method for generating a manipulated data signal for misleading a first machine learning system, which is designed to ascertain a semantic segmentation of a received one-dimensional or multi-dimensional data signal, the method having the following steps: a) ascertaining a desired semantic segmentation of the manipulated data signal; and b) generating the manipulated signal as a function of the received data signal and the ascertained desired semantic segmentation as well as an estimated semantic segmentation of the manipulated data signal.

Abstract: A method for generating a manipulated data signal for misleading a first machine learning system, which is designed to ascertain a semantic segmentation of a received one-dimensional or multi-dimensional data signal, the method having the following steps: a) ascertaining a desired semantic segmentation of the manipulated data signal; and b) generating the manipulated signal as a function of the received data signal and the ascertained desired semantic segmentation as well as an estimated semantic segmentation of the manipulated data signal.

Abstract: A method for generating a manipulated data signal for misleading a first machine learning system, which is designed to ascertain a semantic segmentation of a received one-dimensional or multi-dimensional data signal, the method having the following steps: a) ascertaining a desired semantic segmentation of the manipulated data signal; and b) generating the manipulated signal as a function of the received data signal and the ascertained desired semantic segmentation as well as an estimated semantic segmentation of the manipulated data signal.

Abstract: A method for generating a universal data signal interference for generating a manipulated data signal for deceiving a first machine learning system, which is configured to ascertain a semantic segmentation of a received one-dimensional or multidimensional data signal, The method includes a) ascertaining a training data set that includes pairs of data signals and associated desired semantic segmentations, b) generating the data signal interference, as a function of the data signals of the training data set, of the associated desired semantic segmentation, as well as of estimated semantic segmentations of the data signals acted upon by the data signal interference.