Malicious application of deepfakes (i.e., technologies can generate target faces or face attributes) has posed a huge threat to our society. The fake multimedia content generated by deepfake models can harm the reputation and even threaten the property of the person who has been impersonated. Fortunately, the adversarial watermark could be used for combating deepfake models, leading them to generate distorted images. The existing methods require an individual training process for every facial image, to generate the adversarial watermark against a specific deepfake model, which are extremely inefficient. To address this problem, we propose a universal adversarial attack method on deepfake models, to generate a Cross-Model Universal Adversarial Watermark (CMUA-Watermark) that can protect thousands of facial images from multiple deepfake models. Specifically, we first propose a cross-model universal attack pipeline by attacking multiple deepfake models and combining gradients from these models iteratively. Then we introduce a batch-based method to alleviate the conflict of adversarial watermarks generated by different facial images. Finally, we design a more reasonable and comprehensive evaluation method for evaluating the effectiveness of the adversarial watermark. Experimental results demonstrate that the proposed CMUA-Watermark can effectively distort the fake facial images generated by deepfake models and successfully protect facial images from deepfakes in real scenes.

Heavy-tailed distributions have been studied in statistics, random matrix theory, physics, and econometrics as models of correlated systems, among other domains. Further, heavy-tail distributed eigenvalues of the covariance matrix of the weight matrices in neural networks have been shown to empirically correlate with test set accuracy in several works (e.g. arXiv:1901.08276), but a formal relationship between heavy-tail distributed parameters and generalization bounds was yet to be demonstrated. In this work, the compression framework of arXiv:1802.05296 is utilized to show that matrices with heavy-tail distributed matrix elements can be compressed, resulting in networks with sparse weight matrices. Since the parameter count has been reduced to a sum of the non-zero elements of sparse matrices, the compression framework allows us to bound the generalization gap of the resulting compressed network with a non-vacuous generalization bound. Further, the action of these matrices on a vector is discussed, and how they may relate to compression and resilient classification is analyzed.

Machine learning algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to degrade the algorithms' performance. We show that current approaches, which typically assume that regularization hyperparameters remain constant, lead to an overly pessimistic view of the algorithms' robustness and of the impact of regularization. We propose a novel optimal attack formulation that considers the effect of the attack on the hyperparameters, modelling the attack as a \emph{minimax bilevel optimization problem}. This allows to formulate optimal attacks, select hyperparameters and evaluate robustness under worst case conditions. We apply this formulation to logistic regression using $L_2$ regularization, empirically show the limitations of previous strategies and evidence the benefits of using $L_2$ regularization to dampen the effect of poisoning attacks.

Continual learning (CL) -- the ability to continuously learn, building on previously acquired knowledge -- is a natural requirement for long-lived autonomous reinforcement learning (RL) agents. While building such agents, one needs to balance opposing desiderata, such as constraints on capacity and compute, the ability to not catastrophically forget, and to exhibit positive transfer on new tasks. Understanding the right trade-off is conceptually and computationally challenging, which we argue has led the community to overly focus on catastrophic forgetting. In response to these issues, we advocate for the need to prioritize forward transfer and propose Continual World, a benchmark consisting of realistic and meaningfully diverse robotic tasks built on top of Meta-World [52] as a testbed. Following an in-depth empirical evaluation of existing CL methods, we pinpoint their limitations and highlight unique algorithmic challenges in the RL setting. Our benchmark aims to provide a meaningful and computationally inexpensive challenge for the community and thus help better understand the performance of existing and future solutions.

We introduce a novel top-down end-to-end formulation of document-level discourse parsing in the Rhetorical Structure Theory (RST) framework. In this formulation, we consider discourse parsing as a sequence of splitting decisions at token boundaries and use a seq2seq network to model the splitting decisions. Our framework facilitates discourse parsing from scratch without requiring discourse segmentation as a prerequisite; rather, it yields segmentation as part of the parsing process. Our unified parsing model adopts a beam search to decode the best tree structure by searching through a space of high-scoring trees. With extensive experiments on the standard English RST discourse treebank, we demonstrate that our parser outperforms existing methods by a good margin in both end-to-end parsing and parsing with gold segmentation. More importantly, it does so without using any handcrafted features, making it faster and easily adaptable to new languages and domains.

As the market leader in analytics, SAS empowers organizations to create and sustain true value from diverse IoT data and initiatives – whether that data is at the edge, in the cloud or anywhere in between. From visualization and statistical modeling to descriptive, predictive and prescriptive analytics, SAS delivers deep expertise in IoT analytics – including AI, machine learning and deep learning – to help you reduce risk and gain real business value.

Serverless computing is a new type of cloud-based computation infrastructure initially developed for web microservices and IoT applications. As it frees model developers from concerns regarding capacity planning, configuration, management, maintenance, operating and scaling of containers, VMs and physical servers, serverless computing has gained popularity with machine learning (ML) researchers in recent years. Moreover, the benefits of serverless computing have also piqued interest in adopting it to data-intensive workloads such as ETL (extract, transform, load), query processing and ML, where it can provide significant cost reductions. Riding this trend, a research team from ETH Zürich and Microsoft recently conducted a systematic, comparative study of distributed ML training over serverless infrastructures (FaaS) and "serverful" infrastructures (IaaS), aiming to identify and understand the system tradeoffs involved in distributed ML training with serverless infrastructures. Serverless computing is offered by major cloud service providers such as AWS Lambda, Azure Functions and Google Cloud Functions.

Artificial intelligence tool can be used for long-term tracking and management of chronic gastrointestinal ailments. An artificial intelligence tool under development at Duke University can be added to the standard toilet to help analyze patients' stool and give gastroenterologists the information they need to provide appropriate treatment, according to research that was selected for presentation at Digestive Disease Week (DDW) 2021. The new technology could assist in managing chronic gastrointestinal issues such as inflammatory bowel disease (IBD) and irritable bowel syndrome (IBS). "Typically, gastroenterologists have to rely on patient self-reported information about their stool to help determine the cause of their gastrointestinal health issues, which can be very unreliable," said Deborah Fisher, MD, one of the lead authors on the study and associate professor of medicine at Duke University Durham, North Carolina. "Patients often can't remember what their stool looks like or how often they have a bowel movement, which is part of the standard monitoring process. The Smart Toilet technology will allow us to gather the long-term information needed to make a more accurate and timely diagnosis of chronic gastrointestinal problems."

Despite the many ominous connotations trumpeted in works of fiction, the adoption and growth of AI can is simply another phase of the technological advance that has marked the development of human society. Yet, because we associate intelligence with living creatures, particularly our own species, the idea of machines that possess that faculty excites some trepidation. AI agents may turn out to be as unpredictable and perverse as any intelligent human. No such worry is evident in Silicon Valley. Sundar Pichai, Google's chief, speaking at the World Economic Forum in Davos, Switzerland, enthused about the technology: "AI is probably the most important thing humanity has ever worked on. I think of it as something more profound than electricity or fire," he said. Google is a major participant in an AI market that is clipping along at a five-year compound annual growth rate (CAGR) of 17.5%. Globally, the industry is projected to swell to $554.3 billion by 2024. Other players of note are IBM, Intuit, Microsoft, OpenText, Palantir, SAS, and Slack.

You know that expression When you have a hammer, everything looks like a nail? Well, in machine learning, it seems like we really have discovered a magical hammer for which everything is, in fact, a nail, and they're called Transformers. Transformers are models that can be designed to translate text, write poems and op eds, and even generate computer code. In fact, lots of the amazing research I write about on daleonai.com is built on Transformers, like AlphaFold 2, the model that predicts the structures of proteins from their genetic sequences, as well as powerful natural language processing (NLP) models like GPT-3, BERT, T5, Switch, Meena, and others. You might say they're more than meets the… ugh, forget it.