The artificial-intelligence model that powers ChatGPT can create superficially plausible scientific data sets.Credit: Mateusz Slodkowski/SOPA Images/LightRocket via Getty Researchers have used the technology behind the artificial intelligence (AI) chatbot ChatGPT to create a fake clinical-trial data set to support an unverified scientific claim. In a paper published in JAMA Ophthalmology on 9 November1, the authors used GPT-4 -- the latest version of the large language model on which ChatGPT runs -- paired with Advanced Data Analysis (ADA), a model that incorporates the programming language Python and can perform statistical analysis and create data visualizations. The AI-generated data compared the outcomes of two surgical procedures and indicated -- wrongly -- that one treatment is better than the other. "Our aim was to highlight that, in a few minutes, you can create a data set that is not supported by real original data, and it is also opposite or in the other direction compared to the evidence that are available," says study co-author Giuseppe Giannaccare, an eye surgeon at the University of Cagliari in Italy. The ability of AI to fabricate convincing data adds to concern among researchers and journal editors about research integrity.

Researchers in Italy have melded the emerging science of convolutional neural networks (CNNs) with deep learning -- a discipline within artificial intelligence -- to achieve a system of market forecasting with the potential for greater gains and fewer losses than previous attempts to use AI methods to manage stock portfolios. The team, led by Prof. Silvio Barra at the University of Cagliari, published their findings on IEEE/CAA Journal of Automatica Sinica. The University of Cagliari-based team set out to create an AI-managed "buy and hold" (B&H) strategy -- a system of deciding whether to take one of three possible actions -- a long action (buying a stock and selling it before the market closes), a short action (selling a stock, then buying it back before the market closes), and a hold (deciding not to invest in a stock that day). At the heart of their proposed system is an automated cycle of analyzing layered images generated from current and past market data. Older B&H systems based their decisions on machine learning, a discipline that leans heavily on predictions based on past performance.

Sergio Consoli is a Senior Scientist within the Data Science department at Philips Research, Eindhoven, focusing on advancing automated analytical methods used to extract new knowledge from data for health-tech applications. He is author of several research publications in peer-reviewed international journals, edited books, and leading conferences in the fields of his work. Diego Reforgiato Recupero is Associate Professor at the Department of Mathematics and Computer Science of the University of Cagliari, Italy. His interests span from Semantic Web, graph theory and smart grid optimization to sentiment analysis, data mining, big data, machine and deep learning and natural language processing. He is also affiliated within the ISTC institute at the National Research Council (CNR) and co-founder of six ICT companies two of which are university spin-offs.

CA Technologies announced its participation in scientific research to discover how Internet of Things (IoT) applications can use a type of AI known as'deep learning' to imitate human decisions. The research will also explore how to prevent that AI-based decisions are not producing biased results. This three-year research project is named ALOHA (adaptive and secure deep learning on heterogeneous architectures). It is funded by the European Union as part of the Horizon 2020 research and innovation programme, and coordinated by the University of Cagliari in Italy. "The future of all technologies will include AI and deep learning in some way," said Otto Berkes, CTO, CA Technologies.

Adversarial models, already known to defeat the artificial intelligence behind image classifiers and computer audio, are also good at defeating malware detection. Last year, researchers from NVIDIA, Booz Allen Hamilton, and the University of Maryland probably felt justifiably pleased with themselves when they trained a neural network to ingest EXEs and spot malware samples among them. Their MalConv software ran a static analysis on executables (that is, it looked at the binaries but didn't run them), and they claimed up to 98 per cent accuracy in malware classification once their neural network had a big enough learning set. Alas, it's a neural network, and neural networks are subject to adversarial attacks. On Monday March 12th, 2018, this paper (by boffins from the Technical University of Munich, the University of Cagliari in Italy, and Italian company Pluribus One) described one way of defeating MalConv.