Abstract: A computer system (which includes one or more computers) that generates a second autoencoder (AE) neural network (such as an ALAP-AE neural network) is described. During operation, the computer system may obtain information specifying an initial AE neural network. Then, the computer system may compute a subset of filters associated with the initial AE neural network to remove based at least in part on a L1-norm loss function and weights associated with filters in initial AE neural network. Moreover, the computer system may prune the subset of the filters from the initial AE neural network. Next, the computer system may generate the ALAP-AE neural network by retraining the initial AE neural network, where the retraining includes a student-teacher model in which the teacher includes the pruned initial AE neural network and the student includes the ALAP-AE neural network.

Abstract: A computer that identifies a fake image is described. During operation, the computer receives an image. Then, the computer performs analysis on the image to determine a signature that includes multiple features. Based at least in part in the determined signature, the computer classifies the image as having a first signature associated with the fake image or as having a second signature associated with a real image, where the first signature corresponds to a finite resolution of a neural network that generated the fake image, a finite number of parameters in the neural network that generated the fake image, or both. For example, the finite resolution may correspond to floating point operations in the neural network. Moreover, in response to the classification, the computer may perform a remedial action, such as providing a warning or a recommendation, or performing filtering.

Abstract: A computer that identifies a fake image is described. During operation, the computer receives an image. Then, the computer performs analysis on the image to determine a signature that includes multiple features. Based at least in part in the determined signature, the computer classifies the image as having a first signature associated with the fake image or as having a second signature associated with a real image, where the first signature corresponds to a finite resolution of a neural network that generated the fake image, a finite number of parameters in the neural network that generated the fake image, or both. For example, the finite resolution may correspond to floating point operations in the neural network. Moreover, in response to the classification, the computer may perform a remedial action, such as providing a warning or a recommendation, or performing filtering.

Abstract: A computer that identifies a fake image is described. During operation, the computer receives an image. Then, the computer performs analysis on the image to determine a signature that includes multiple features. Based at least in part in the determined signature, the computer classifies the image as having a first signature associated with the fake image or as having a second signature associated with a real image, where the first signature corresponds to a finite resolution of a neural network that generated the fake image, a finite number of parameters in the neural network that generated the fake image, or both. For example, the finite resolution may correspond to floating point operations in the neural network. Moreover, in response to the classification, the computer may perform a remedial action, such as providing a warning or a recommendation, or performing filtering.

Abstract: A computer that identifies a fake image is described. During operation, the computer receives an image. Then, the computer performs analysis on the image to determine a signature that includes multiple features. Based at least in part in the determined signature, the computer classifies the image as having a first signature associated with the fake image or as having a second signature associated with a real image, where the first signature corresponds to a finite resolution of a neural network that generated the fake image, a finite number of parameters in the neural network that generated the fake image, or both. For example, the finite resolution may correspond to floating point operations in the neural network. Moreover, in response to the classification, the computer may perform a remedial action, such as providing a warning or a recommendation, or performing filtering.

Abstract: There are provided systems and methods of optimizing walking machines. The system including a memory storing a software application and a processor configured to execute the software application to receive a character from a user, the character having walking mechanisms, determine optimal design parameters for the character based on the walking mechanisms, and alter the walking mechanisms of the character based on the optimal design parameters to generate altered walking mechanisms, wherein the optimal design parameters are for use by the character to walk using the altered walking mechanisms. Generating the altered walking mechanisms may include at least one of changing locations for joints on the walking mechanisms, changing the dimensions of the walking mechanisms, and changing motion timings for the walking mechanisms.