David Güera

Xiaoming Zhao, Fangchang Ma, David Güera et al. · apple-ml, uw

What is really needed to make an existing 2D GAN 3D-aware? To answer this question, we modify a classical GAN, i.e., StyleGANv2, as little as possible. We find that only two modifications are absolutely necessary: 1) a multiplane image style generator branch which produces a set of alpha maps conditioned on their depth; 2) a pose-conditioned discriminator. We refer to the generated output as a 'generative multiplane image' (GMPI) and emphasize that its renderings are not only high-quality but also guaranteed to be view-consistent, which makes GMPIs different from many prior works. Importantly, the number of alpha maps can be dynamically adjusted and can differ between training and inference, alleviating memory concerns and enabling fast training of GMPIs in less than half a day at a resolution of $1024^2$. Our findings are consistent across three challenging and common high-resolution datasets, including FFHQ, AFHQv2, and MetFaces.

Emily R. Bartusiak, Sri Kalyan Yarlagadda, David Güera et al.

The widespread availability of image editing tools and improvements in image processing techniques allow image manipulation to be very easy. Oftentimes, easy-to-use yet sophisticated image manipulation tools yields distortions/changes imperceptible to the human observer. Distribution of forged images can have drastic ramifications, especially when coupled with the speed and vastness of the Internet. Therefore, verifying image integrity poses an immense and important challenge to the digital forensic community. Satellite images specifically can be modified in a number of ways, including the insertion of objects to hide existing scenes and structures. In this paper, we describe the use of a Conditional Generative Adversarial Network (cGAN) to identify the presence of such spliced forgeries within satellite images. Additionally, we identify their locations and shapes. Trained on pristine and falsified images, our method achieves high success on these detection and localization objectives.

Alvin Wan, Hanxiang Hao, Kaushik Patnaik et al. · apple-ml, berkeley

As neural networks grow in size and complexity, inference speeds decline. To combat this, one of the most effective compression techniques -- channel pruning -- removes channels from weights. However, for multi-branch segments of a model, channel removal can introduce inference-time memory copies. In turn, these copies increase inference latency -- so much so that the pruned model can be slower than the unpruned model. As a workaround, pruners conventionally constrain certain channels to be pruned together. This fully eliminates memory copies but, as we show, significantly impairs accuracy. We now have a dilemma: Remove constraints but increase latency, or add constraints and impair accuracy. In response, our insight is to reorder channels at export time, (1) reducing latency by reducing memory copies and (2) improving accuracy by removing constraints. Using this insight, we design a generic algorithm UPSCALE to prune models with any pruning pattern. By removing constraints from existing pruners, we improve ImageNet accuracy for post-training pruned models by 2.1 points on average -- benefiting DenseNet (+16.9), EfficientNetV2 (+7.9), and ResNet (+6.2). Furthermore, by reordering channels, UPSCALE improves inference speeds by up to 2x over a baseline export.

Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang et al. · apple-ml, cmu

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations such as KV-cache sharing and 2-bit quantization-aware training; and ii a scalable server model built on a novel Parallel-Track Mixture-of-Experts PT-MoE transformer that combines track parallelism, mixture-of-experts sparse computation, and interleaved global-local attention to deliver high quality with competitive cost on Apple's Private Cloud Compute platform. Both models are trained on large-scale multilingual and multimodal datasets sourced via responsible web crawling, licensed corpora, and high-quality synthetic data, then further refined with supervised fine-tuning and reinforcement learning on a new asynchronous platform. The resulting models support several additional languages while understanding images and executing tool calls. In public benchmarks and human evaluations, both the server model and the on-device model match or surpass comparably sized open baselines. A new Swift-centric Foundation Models framework exposes guided generation, constrained tool calling, and LoRA adapter fine-tuning, allowing developers to integrate these capabilities with a few lines of code. The latest advancements in Apple Intelligence models are grounded in our Responsible AI approach with safeguards like content filtering and locale-specific evaluation, as well as our commitment to protecting our users' privacy with innovations like Private Cloud Compute.

Daniel Mas Montserrat, Hanxiang Hao, S. K. Yarlagadda et al.

Altered and manipulated multimedia is increasingly present and widely distributed via social media platforms. Advanced video manipulation tools enable the generation of highly realistic-looking altered multimedia. While many methods have been presented to detect manipulations, most of them fail when evaluated with data outside of the datasets used in research environments. In order to address this problem, the Deepfake Detection Challenge (DFDC) provides a large dataset of videos containing realistic manipulations and an evaluation system that ensures that methods work quickly and accurately, even when faced with challenging data. In this paper, we introduce a method based on convolutional neural networks (CNNs) and recurrent neural networks (RNNs) that extracts visual and temporal features from faces present in videos to accurately detect manipulations. The method is evaluated with the DFDC dataset, providing competitive results compared to other techniques.

Sri Kalyan Yarlagadda, Sriram Baireddy, David Güera et al.

It is well known that dietary habits have a significant influence on health. While many studies have been conducted to understand this relationship, little is known about the relationship between eating environments and health. Yet researchers and health agencies around the world have recognized the eating environment as a promising context for improving diet and health. In this paper, we propose an image clustering method to automatically extract the eating environments from eating occasion images captured during a community dwelling dietary study. Specifically, we are interested in learning how many different environments an individual consumes food in. Our method clusters images by extracting features at both global and local scales using a deep neural network. The variation in the number of clusters and images captured by different individual makes this a very challenging problem. Experimental results show that our method performs significantly better compared to several existing clustering approaches.

Hanxiang Hao, David Güera, Amy R. Reibman et al.

From TV news to Google StreetView, face obscuration has been used for privacy protection. Due to recent advances in the field of deep learning, obscuration methods such as Gaussian blurring and pixelation are not guaranteed to conceal identity. In this paper, we propose a utility-preserving generative model, UP-GAN, that is able to provide an effective face obscuration, while preserving facial utility. By utility-preserving we mean preserving facial features that do not reveal identity, such as age, gender, skin tone, pose, and expression. We show that the proposed method achieves the best performance in terms of obscuration and utility preservation.

David Güera, Sriram Baireddy, Paolo Bestagini et al.

Manipulating video content is easier than ever. Due to the misuse potential of manipulated content, multiple detection techniques that analyze the pixel data from the videos have been proposed. However, clever manipulators should also carefully forge the metadata and auxiliary header information, which is harder to do for videos than images. In this paper, we propose to identify forged videos by analyzing their multimedia stream descriptors with simple binary classifiers, completely avoiding the pixel space. Using well-known datasets, our results show that this scalable approach can achieve a high manipulation detection score if the manipulators have not done a careful data sanitization of the multimedia stream descriptors.

Hanxiang Hao, David Güera, János Horváth et al.

Face obscuration is needed by law enforcement and mass media outlets to guarantee privacy. Sharing sensitive content where obscuration or redaction techniques have failed to completely remove all identifiable traces can lead to many legal and social issues. Hence, we need to be able to systematically measure the face obscuration performance of a given technique. In this paper we propose to measure the effectiveness of eight obscuration techniques. We do so by attacking the redacted faces in three scenarios: obscured face identification, verification, and reconstruction. Threat modeling is also considered to provide a vulnerability analysis for each studied obscuration technique. Based on our evaluation, we show that the k-same based methods are the most effective.

Javier Ribera, David Güera, Yuhao Chen et al.

Recent advances in convolutional neural networks (CNN) have achieved remarkable results in locating objects in images. In these networks, the training procedure usually requires providing bounding boxes or the maximum number of expected objects. In this paper, we address the task of estimating object locations without annotated bounding boxes which are typically hand-drawn and time consuming to label. We propose a loss function that can be used in any fully convolutional network (FCN) to estimate object locations. This loss function is a modification of the average Hausdorff distance between two unordered sets of points. The proposed method has no notion of bounding boxes, region proposals, or sliding windows. We evaluate our method with three datasets designed to locate people's heads, pupil centers and plant centers. We outperform state-of-the-art generic object detectors and methods fine-tuned for pupil tracking.

David Güera, Yu Wang, Luca Bondi et al.

An increasing number of digital images are being shared and accessed through websites, media, and social applications. Many of these images have been modified and are not authentic. Recent advances in the use of deep convolutional neural networks (CNNs) have facilitated the task of analyzing the veracity and authenticity of largely distributed image datasets. We examine in this paper the problem of identifying the camera model or type that was used to take an image and that can be spoofed. Due to the linear nature of CNNs and the high-dimensionality of images, neural networks are vulnerable to attacks with adversarial examples. These examples are imperceptibly different from correctly classified images but are misclassified with high confidence by CNNs. In this paper, we describe a counter-forensic method capable of subtly altering images to change their estimated camera model when they are analyzed by any CNN-based camera model detector. Our method can use both the Fast Gradient Sign Method (FGSM) or the Jacobian-based Saliency Map Attack (JSMA) to craft these adversarial images and does not require direct access to the CNN. Our results show that even advanced deep learning architectures trained to analyze images and obtain camera model information are still vulnerable to our proposed method.

David Güera, Sri Kalyan Yarlagadda, Paolo Bestagini et al.

Among the image forensic issues investigated in the last few years, great attention has been devoted to blind camera model attribution. This refers to the problem of detecting which camera model has been used to acquire an image by only exploiting pixel information. Solving this problem has great impact on image integrity assessment as well as on authenticity verification. Recent advancements that use convolutional neural networks (CNNs) in the media forensic field have enabled camera model attribution methods to work well even on small image patches. These improvements are also important for determining forgery localization. Some patches of an image may not contain enough information related to the camera model (e.g., saturated patches). In this paper, we propose a CNN-based solution to estimate the camera model attribution reliability of a given image patch. We show that we can estimate a reliability-map indicating which portions of the image contain reliable camera traces. Testing using a well known dataset confirms that by using this information, it is possible to increase small patch camera model attribution accuracy by more than 8% on a single patch.

Sri Kalyan Yarlagadda, David Güera, Paolo Bestagini et al.

Current satellite imaging technology enables shooting high-resolution pictures of the ground. As any other kind of digital images, overhead pictures can also be easily forged. However, common image forensic techniques are often developed for consumer camera images, which strongly differ in their nature from satellite ones (e.g., compression schemes, post-processing, sensors, etc.). Therefore, many accurate state-of-the-art forensic algorithms are bound to fail if blindly applied to overhead image analysis. Development of novel forensic tools for satellite images is paramount to assess their authenticity and integrity. In this paper, we propose an algorithm for satellite image forgery detection and localization. Specifically, we consider the scenario in which pixels within a region of a satellite image are replaced to add or remove an object from the scene. Our algorithm works under the assumption that no forged images are available for training. Using a generative adversarial network (GAN), we learn a feature representation of pristine satellite images. A one-class support vector machine (SVM) is trained on these features to determine their distribution. Finally, image forgeries are detected as anomalies. The proposed algorithm is validated against different kinds of satellite images containing forgeries of different size and shape.

Luca Bondi, Luca Baroffio, David Güera et al.

Detecting the camera model used to shoot a picture enables to solve a wide series of forensic problems, from copyright infringement to ownership attribution. For this reason, the forensic community has developed a set of camera model identification algorithms that exploit characteristic traces left on acquired images by the processing pipelines specific of each camera model. In this paper, we investigate a novel approach to solve camera model identification problem. Specifically, we propose a data-driven algorithm based on convolutional neural networks, which learns features characterizing each camera model directly from the acquired pictures. Results on a well-known dataset of 18 camera models show that: (i) the proposed method outperforms up-to-date state-of-the-art algorithms on classification of 64x64 color image patches; (ii) features learned by the proposed network generalize to camera models never used for training.