The recent advances in language modeling significantly improved the generative capabilities of deep neural models: in 2019 OpenAI released GPT-2, a pre-trained language model that can autonomously generate coherent, non-trivial and human-like text samples. Since then, ever more powerful text generative models have been developed. Adversaries can exploit these tremendous generative capabilities to enhance social bots that will have the ability to write plausible deepfake messages, hoping to contaminate public debate. To prevent this, it is crucial to develop deepfake social media messages detection systems. However, to the best of our knowledge no one has ever addressed the detection of machine-generated texts on social networks like Twitter or Facebook. With the aim of helping the research in this detection field, we collected the first dataset of real deepfake tweets, TweepFake. It is real in the sense that each deepfake tweet was actually posted on Twitter. We collected tweets from a total of 23 bots, imitating 17 human accounts. The bots are based on various generation techniques, i.e., Markov Chains, RNN, RNN+Markov, LSTM, GPT-2. We also randomly selected tweets from the humans imitated by the bots to have an overall balanced dataset of 25,572 tweets (half human and half bots generated). The dataset is publicly available on Kaggle. Lastly, we evaluated 13 deepfake text detection methods (based on various state-of-the-art approaches) to both demonstrate the challenges that Tweepfake poses and create a solid baseline of detection techniques. We hope that TweepFake can offer the opportunity to tackle the deepfake detection on social media messages as well.

No abstract

In the last years, smart-shoes moved from the medical domain, where they are used to collect gait-related data during rehabilitation or in case of pathologies, to the every-day life of an increasing number of people. In this paper, a method useful to effortlessly authenticate the user during gait periods is proposed. The method relies on the information collected by shoe-mounted accelerometers and gyroscopes, and on the distance between feet collected by Ultra-WideBand (UWB) transceivers. Experimental results show that a balanced accuracy equal to 97% can be achieved even when information about the possible impostors is not known in advance. The contribution of the different information sources, accelerometer, gyroscope, and UWB, is also evaluated.

In the last years there has been a growing attention towards predicting the political orientation of active social media users, being this of great help to study political forecasts, opinion dynamics modeling and users polarization. Existing approaches, mainly targeting Twitter users, rely on content-based analysis or are based on a mixture of content, network and communication analysis. The recent research perspective exploits the fact that a user's political affinity mainly depends on his/her positions on major political and social issues, thus shifting the focus on detecting the stance of users through user-generated content shared on social networks. The work herein described focuses on a completely unsupervised stance detection framework that predicts the user's stance (along five levels of agreement) about specific social-political statements by exploiting content-based analysis of its Twitter timeline. The ground-truth user's stance may come from Voting Advice Applications (VAAs), online tools that help citizens to identify their political leanings by comparing their political preferences with party political stances. Starting from the knowledge of the agreement level of six parties on 20 different statements (VAA's statements), the objective of the study is to predict the stance of a Party p in regard to each statement s exploiting what the Twitter Party account wrote on Twitter. To this end we propose T weets2Stance (T 2S), a novel and totally unsupervised stance detector framework which relies on the zero-shot learning technique to quickly and accurately operate on non-labeled data. Interestingly, T2S can be applied to any social media user for any context of interest, not limited to the political one. Results obtained from multiple experiments (analysis, measurement, and evaluation) show that, although the general maximum F1 value is 0.4, T 2S can correctly predict the stance with a general minimum MAE of 1.13, which is a great achievement considering the task complexity.