Machine Hallucinations -- Space: Metaverse is a breathtaking collection from digital media artist Refik Anadol. It includes richly diverse artworks inspired by his studio's collaboration with NASA JPL which began in early 2018, and his long-term research into the photographic history of space exploration. Using advanced machine learning algorithms trained specifically on photographs of deep space captured by satellites and spacecrafts throughout humanity's quest to explore its depths, Anadol creates mesmerizing visual speculations of the unknown. The works explore our fascination with the subject while unveiling intricate connections between obscurity and openness through both digital and physical mediums. Studying the visuals that have been captured by the most comprehensive machines sent to outer space inspired Anadol to contemplate the idea that telescopes keep visual travel journals of spaces where humans cannot yet travel.

The major aim of this paper is to explain the data poisoning attacks using label-flipping during the training stage of the electroencephalogram (EEG) signal-based human emotion evaluation systems deploying Machine Learning models from the attackers' perspective. Human emotion evaluation using EEG signals has consistently attracted a lot of research attention. The identification of human emotional states based on EEG signals is effective to detect potential internal threats caused by insider individuals. Nevertheless, EEG signal-based human emotion evaluation systems have shown several vulnerabilities to data poison attacks. The findings of the experiments demonstrate that the suggested data poison assaults are model-independently successful, although various models exhibit varying levels of resilience to the attacks. In addition, the data poison attacks on the EEG signal-based human emotion evaluation systems are explained with several Explainable Artificial Intelligence (XAI) methods, including Shapley Additive Explanation (SHAP) values, Local Interpretable Model-agnostic Explanations (LIME), and Generated Decision Trees. And the codes of this paper are publicly available on GitHub.

A recent increase in data availability has allowed the possibility to perform different statistical linguistic studies. Here we use the Google Books Ngram dataset to analyze word flow among English, French, German, Italian, and Spanish. We study what we define as ``migrant words'', a type of loanwords that do not change their spelling. We quantify migrant words from one language to another for different decades, and notice that most migrant words can be aggregated in semantic fields and associated to historic events. We also study the statistical properties of accumulated migrant words and their rank dynamics. We propose a measure of use of migrant words that could be used as a proxy of cultural influence. Our methodology is not exempt of caveats, but our results are encouraging to promote further studies in this direction.

Robot-guided catheter insertion has the potential to deliver urgent medical care in situations where medical personnel are unavailable. However, this technique requires accurate and reliable segmentation of anatomical landmarks in the body. For the ultrasound imaging modality, obtaining large amounts of training data for a segmentation model is time-consuming and expensive. This paper introduces RESUS (RESlicing of UltraSound Images), a weak supervision data augmentation technique for ultrasound images based on slicing reconstructed 3D volumes from tracked 2D images. This technique allows us to generate views which cannot be easily obtained in vivo due to physical constraints of ultrasound imaging, and use these augmented ultrasound images to train a semantic segmentation model. We demonstrate that RESUS achieves statistically significant improvement over training with non-augmented images and highlight qualitative improvements through vessel reconstruction.

Artificial Intelligence is being employed by humans to collaboratively solve complicated tasks for search and rescue, manufacturing, etc. Efficient teamwork can be achieved by understanding user preferences and recommending different strategies for solving the particular task to humans. Prior work has focused on personalization of recommendation systems for relatively well-understood tasks in the context of e-commerce or social networks. In this paper, we seek to understand the important factors to consider while designing user-centric strategy recommendation systems for decision-making. We conducted a human-subjects experiment (n=60) for measuring the preferences of users with different personality types towards different strategy recommendation systems. We conducted our experiment across four types of strategy recommendation modalities that have been established in prior work: (1) Single strategy recommendation, (2) Multiple similar recommendations, (3) Multiple diverse recommendations, (4) All possible strategies recommendations. While these strategy recommendation schemes have been explored independently in prior work, our study is novel in that we employ all of them simultaneously and in the context of strategy recommendations, to provide us an in-depth overview of the perception of different strategy recommendation systems. We found that certain personality traits, such as conscientiousness, notably impact the preference towards a particular type of system (p < 0.01). Finally, we report an interesting relationship between usability, alignment and perceived intelligence wherein greater perceived alignment of recommendations with one's own preferences leads to higher perceived intelligence (p < 0.01) and higher usability (p < 0.01).

Learning from raw high dimensional data via interaction with a given environment has been effectively achieved through the utilization of deep neural networks. Yet the observed degradation in policy performance caused by imperceptible worst-case policy dependent translations along high sensitivity directions (i.e. adversarial perturbations) raises concerns on the robustness of deep reinforcement learning policies. In our paper, we show that these high sensitivity directions do not lie only along particular worst-case directions, but rather are more abundant in the deep neural policy landscape and can be found via more natural means in a black-box setting. Furthermore, we show that vanilla training techniques intriguingly result in learning more robust policies compared to the policies learnt via the state-of-the-art adversarial training techniques. We believe our work lays out intriguing properties of the deep reinforcement learning policy manifold and our results can help to build robust and generalizable deep reinforcement learning policies.

Neural Networks are infamously sensitive to small perturbations in their inputs, making them vulnerable to adversarial attacks. This project evaluates the performance of Denoising Diffusion Probabilistic Models (DDPM) as a purification technique to defend against adversarial attacks. This works by adding noise to an adversarial example before removing it through the reverse process of the diffusion model. We evaluate the approach on the PatchCamelyon data set for histopathologic scans of lymph node sections and find an improvement of the robust accuracy by up to 88\% of the original model's accuracy, constituting a considerable improvement over the vanilla model and our baselines. The project code is located at https://github.com/ankile/Adversarial-Diffusion.

Recent years have seen a growth in the number of industrial robots working closely with end-users such as factory workers. This growing use of collaborative robots has been enabled in part due to the availability of end-user robot programming methods that allow users who are not robot programmers to teach robots task actions. Programming by Demonstration (PbD) is one such end-user programming method that enables users to bypass the complexities of specifying robot motions using programming languages by instead demonstrating the desired robot behavior. Demonstrations are often provided by physically guiding the robot through the motions required for a task action in a process known as kinesthetic teaching. Kinesthetic teaching enables users to directly demonstrate task behaviors in the robot's configuration space, making it a popular end-user robot programming method for collaborative robots known for its low cognitive burden. However, because kinesthetic teaching restricts the programmer's teaching to motion demonstrations, it fails to leverage information from other modalities that humans naturally use when providing physical task demonstrations to one other, such as gaze and speech. Incorporating multimodal information into the traditional kinesthetic programming workflow has the potential to enhance robot learning by highlighting critical aspects of a program, reducing ambiguity, and improving situational awareness for the robot learner and can provide insight into the human programmer's intent and difficulties. In this extended abstract, we describe a preliminary study on multimodal kinesthetic demonstrations and future directions for using multimodal demonstrations to enhance robot learning and user programming experiences.

Large-scale online campaigns, malicious or otherwise, require a significant degree of coordination among participants, which sparked interest in the study of coordinated online behavior. State-of-the-art methods for detecting coordinated behavior perform static analyses, disregarding the temporal dynamics of coordination. Here, we carry out the first dynamic analysis of coordinated behavior. To reach our goal we build a multiplex temporal network and we perform dynamic community detection to identify groups of users that exhibited coordinated behaviors in time. Thanks to our novel approach we find that: (i) coordinated communities feature variable degrees of temporal instability; (ii) dynamic analyses are needed to account for such instability, and results of static analyses can be unreliable and scarcely representative of unstable communities; (iii) some users exhibit distinct archetypal behaviors that have important practical implications; (iv) content and network characteristics contribute to explaining why users leave and join coordinated communities. Our results demonstrate the advantages of dynamic analyses and open up new directions of research on the unfolding of online debates, on the strategies of coordinated communities, and on the patterns of online influence.

This is a weekly newsletter exploring the collision of technology and humanity. What's exciting about AI right now is that the platform layer is solidifying, meaning that it's time for the application layer to emerge. Over the past few months, I've written several Digital Native pieces about what's happening in AI. Given that this is the topic in tech as we head into 2023, I wanted to combine those pieces into one cohesive deep-dive on AI, and then expand upon them. The result is that this is a longer piece than usual, but my hope is that it offers a "state of the union" snapshot for where we are and a hint at where we might be going. When I think about what's happening in artificial intelligence, I tend to think of two movies. One came out 33 years ago, and one came out 10 months ago. Hyperland is a mostly-forgotten 1990 film written by Douglas Adams, an author best known for writing The Hitchhiker's Guide to the Galaxy. The premise of Hyperland (which you can watch on YouTube here) is that Adams is fed up by passive linear TV--what the film calls "the sort of television that just happens at you, that you just sit in front of like a couch potato." Seeking a more interactive form of media, Adams takes his TV to a dump, where he meets Tom (played by Tom Baker). Tom is a software agent--essentially, a digital butler capable of personalizing your information and entertainment diet to your specific interests. Tom takes our protagonist through a virtual land of hypermedia--linked text, sounds, images, and videos. In other words, Tom takes Adams on a journey through the internet.