Worldwide Artificial intelligence (AI) software revenue is forecast to total $62.5 billion in 2022, an increase of 21.3% from 2021, according to a new forecast from Gartner, Inc. Many enterprises are boosting spending on AI as they seek better processes to develop applications. Today's leading AI companies are expanding their technological reach through other technology categories and operations, ranging from predictive analytics to business intelligence to data warehouse tools to deep learning, alleviating several industrial and personal pain points. "The AI software market is picking up speed, but its long-term trajectory will depend on enterprises advancing their AI maturity," said Alys Woodward, senior research director at Gartner. The AI software market encompasses applications with AI embedded in them, such as computer vision software, as well as software that is used to build AI systems.

The metaverse: while some of us are still coming to terms with the idea that we're likely to spend increasing amounts of time in a 3D version of the internet, companies are already scrambling to define the space, carve out their niche, and even snap up virtual real estate. The shift to the metaverse is likely to have a positive business impact, according to 71% of respondents to an Accenture survey, and 42% say it will be "breakthrough" or "transformational." The metaverse will infiltrate every sector in the coming years, culminating in a market opportunity worth more than $1 trillion in annual revenues, according to JP Morgan. Mark Zuckerberg's Meta says the metaverse will be "the biggest opportunity for modern business since the creation of the internet". He has outlined plans to spend more than $10 billion on developing virtual reality software and hardware.

Beneath the buzz, the metaverse is arriving in both predictable and unexpected ways. Some new experiences using headsets and mixed reality will be in your face – quite literally – but other implications will be harder to spot. As with all new categories, we'll see intended and unintended innovations and experiences, and the security stakes will be higher than we imagine at first. There is an inherent social engineering advantage with the novelty of any new technology. In the metaverse, fraud and phishing attacks targeting your identity could come from a familiar face – literally – like an avatar who impersonates your coworker, instead of a misleading domain name or email address.

Arising out of fusion problems that exist in a variety of fields in the natural and life sciences, the methods available to fuse multiple data sets have expanded dramatically in recent years. Older methods, rooted in psychometrics and chemometrics, also exist. Multiblock Data Fusion in Statistics and Machine Learning: Applications in the Natural and Life Sciences is a detailed overview of all relevant multiblock data analysis methods for fusing multiple data sets. It focuses on methods based on components and latent variables, including both well-known and lesser-known methods with potential applications in different types of problems. Many of the included methods are illustrated by practical examples and are accompanied by a freely available R-package.

We investigate a new threat to neural sequence-to-sequence (seq2seq) models: training-time attacks that cause models to "spin" their outputs so as to support an adversary-chosen sentiment or point of view -- but only when the input contains adversary-chosen trigger words. For example, a spinned summarization model outputs positive summaries of any text that mentions the name of some individual or organization. Model spinning introduces a "meta-backdoor" into a model. Whereas conventional backdoors cause models to produce incorrect outputs on inputs with the trigger, outputs of spinned models preserve context and maintain standard accuracy metrics, yet also satisfy a meta-task chosen by the adversary. Model spinning enables propaganda-as-a-service, where propaganda is defined as biased speech. An adversary can create customized language models that produce desired spins for chosen triggers, then deploy these models to generate disinformation (a platform attack), or else inject them into ML training pipelines (a supply-chain attack), transferring malicious functionality to downstream models trained by victims. To demonstrate the feasibility of model spinning, we develop a new backdooring technique. It stacks an adversarial meta-task onto a seq2seq model, backpropagates the desired meta-task output to points in the word-embedding space we call "pseudo-words," and uses pseudo-words to shift the entire output distribution of the seq2seq model. We evaluate this attack on language generation, summarization, and translation models with different triggers and meta-tasks such as sentiment, toxicity, and entailment. Spinned models largely maintain their accuracy metrics (ROUGE and BLEU) while shifting their outputs to satisfy the adversary's meta-task. We also show that, in the case of a supply-chain attack, the spin functionality transfers to downstream models.

Conversational designers have training and expertise in crafting engaging conversations. Generally conversations are crafted around products and services. Hence a big part of the process is to improve the conversations by focusing & improving the design. For conversational interfaces, a big cause of missed intents from user utterances are new product and new services. The problem here is customers want to chat to your chatbot based on advertising and marketing, but the intents have not been updated.

Consider an alternative history for the war in Ukraine. Intrepid Ukrainian Army units mount an effort to pick off Russian supply convoys. But rather than rely on sporadic air cover, the Russian convoys travel under a blanket of cheap drones. The armed drones carry relatively simple artificial intelligence (AI) that can identify human forms and target them with missiles. The tactic claims many innocent civilians, as the drones kill nearly anyone close enough to the convoys to threaten them with anti-tank weapons.

On a sunny morning last December, Iyus Ruswandi, a 35-year-old furniture maker in the village of Gunungguruh, Indonesia, was woken up early by his mother. A technology company was holding some kind of "social assistance giveaway" at the local Islamic elementary school, she said, and she urged him to go. When he got there, representatives of Worldcoin were collecting emails and phone numbers, or aiming a futuristic metal orb at villagers' faces to scan their irises and other biometric data. Two months before Worldcoin appeared in Ruswandi's village, the San Francisco–based company called Tools for Humanity emerged from stealth mode. The company's website described Worldcoin as an Ethereum-based "new, collectively owned global currency that will be distributed fairly to as many people as possible."

Highly accurate different horizon-based wind speed forecasting facilitates a better modern power system. This paper proposed a novel astute hybrid wind speed forecasting model and applied it to different horizons. The proposed hybrid forecasting model decomposes the original wind speed data into IMFs (Intrinsic Mode Function) using Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN). We fed the obtained subseries from ICEEMDAN to the transformer network. Each transformer network computes the forecast subseries and then passes to the fusion phase. Get the primary wind speed forecasting from the fusion of individual transformer network forecast subseries. Estimate the residual error values and predict errors using a multilayer perceptron neural network. The forecast error is added to the primary forecast wind speed to leverage the high accuracy of wind speed forecasting. Comparative analysis with real-time Kethanur, India wind farm dataset results reveals the proposed ICEEMDAN-TNF-MLPN-RECS hybrid model's superior performance with MAE=1.7096*10^-07, MAPE=2.8416*10^-06, MRE=2.8416*10^-08, MSE=5.0206*10^-14, and RMSE=2.2407*10^-07 for case study 1 and MAE=6.1565*10^-07, MAPE=9.5005*10^-06, MRE=9.5005*10^-08, MSE=8.9289*10^-13, and RMSE=9.4493*10^-07 for case study 2 enriched wind speed forecasting than state-of-the-art methods and reduces the burden on the power system engineer.

Recent infectious disease outbreaks, such as the COVID-19 pandemic and the Zika epidemic in Brazil, have demonstrated both the importance and difficulty of accurately forecasting novel infectious diseases. When new diseases first emerge, we have little knowledge of the transmission process, the level and duration of immunity to reinfection, or other parameters required to build realistic epidemiological models. Time series forecasts and machine learning, while less reliant on assumptions about the disease, require large amounts of data that are also not available in early stages of an outbreak. In this study, we examine how knowledge of related diseases can help make predictions of new diseases in data-scarce environments using transfer learning. We implement both an empirical and a theoretical approach. Using empirical data from Brazil, we compare how well different machine learning models transfer knowledge between two different disease pairs: (i) dengue and Zika, and (ii) influenza and COVID-19. In the theoretical analysis, we generate data using different transmission and recovery rates with an SIR compartmental model, and then compare the effectiveness of different transfer learning methods. We find that transfer learning offers the potential to improve predictions, even beyond a model based on data from the target disease, though the appropriate source disease must be chosen carefully. While imperfect, these models offer an additional input for decision makers during pandemic response.