Music adversarial attacks have garnered significant interest in the field of Music Information Retrieval (MIR). In this paper, we present Music Adversarial Inpainting Attack (MAIA), a novel adversarial attack framework that supports both white-box and black-box attack scenarios. MAIA begins with an importance analysis to identify critical audio segments, which are then targeted for modification. Utilizing generative inpainting models, these segments are reconstructed with guidance from the output of the attacked model, ensuring subtle and effective adversarial perturbations. We evaluate MAIA on multiple MIR tasks, demonstrating high attack success rates in both white-box and black-box settings while maintaining minimal perceptual distortion. Additionally, subjective listening tests confirm the high audio fidelity of the adversarial samples. Our findings highlight vulnerabilities in current MIR systems and emphasize the need for more robust and secure models.

Artificial Intelligence (AI) integration in healthcare has emerged as a transfor-mative force, promising to revolutionize patient care, optimize resource allocation, and enhance clinical decision-making [2, 10]. As the healthcare ecosystem increasingly recognizes the importance of AI-powered tools, there is a growing need for collaborative platforms to facilitate the development, deployment, and management of AI solutions in medical settings [7, 13]. Modern healthcare institutions are facing complex challenges that demand sophisticated technological solutions. A comprehensive Medical AI Platform can serve as a powerful foundation for addressing these complex needs, effectively bridging technological capabilities with clinical requirements. One of the open challenges in healthcare is the management of the vast amounts of data handled in clinical settings. Cloud-based medical AI platforms can provide new opportunities for computational resource sharing, enabling institutions to optimize data storage, and collaborative research environments. By creating a unified and standardised ecosystem, these platforms break down traditional institutional barriers, facilitating knowledge exchange between medical professionals, data scientists, and researchers.

Predicting player behavior in strategic games, especially complex ones like chess, presents a significant challenge. The difficulty arises from several factors. First, the sheer number of potential outcomes stemming from even a single position, starting from the initial setup, makes forecasting a player's next move incredibly complex. Second, and perhaps even more challenging, is the inherent unpredictability of human behavior. Unlike the optimized play of engines, humans introduce a layer of variability due to differing playing styles and decision-making processes. Each player approaches the game with a unique blend of strategic thinking, tactical awareness, and psychological tendencies, leading to diverse and often unexpected actions. This stylistic variation, combined with the capacity for creativity and even irrational moves, makes predicting human play difficult. Chess, a longstanding benchmark of artificial intelligence research, has seen significant advancements in tools and automation. Engines like Deep Blue, AlphaZero, and Stockfish can defeat even the most skilled human players. However, despite their exceptional ability to outplay top-level grandmasters, predicting the moves of non-grandmaster players, who comprise most of the global chess community -- remains complicated for these engines. This paper proposes a novel approach combining expert knowledge with machine learning techniques to predict human players' next moves. By applying feature engineering grounded in domain expertise, we seek to uncover the patterns in the moves of intermediate-level chess players, particularly during the opening phase of the game. Our methodology offers a promising framework for anticipating human behavior, advancing both the fields of AI and human-computer interaction.

AI research in chess has been primarily focused on producing stronger agents that can maximize the probability of winning. However, there is another aspect to chess that has largely gone unexamined: its aesthetic appeal. Specifically, there exists a category of chess moves called ``brilliant" moves. These moves are appreciated and admired by players for their high intellectual aesthetics. We demonstrate the first system for classifying chess moves as brilliant. The system uses a neural network, using the output of a chess engine as well as features that describe the shape of the game tree. The system achieves an accuracy of 79% (with 50% base-rate), a PPV of 83%, and an NPV of 75%. We demonstrate that what humans perceive as ``brilliant" moves is not merely the best possible move. We show that a move is more likely to be predicted as brilliant, all things being equal, if a weaker engine considers it lower-quality (for the same rating by a stronger engine). Our system opens the avenues for computer chess engines to (appear to) display human-like brilliance, and, hence, creativity.

Powerful artificial intelligence systems are often used in settings where they must interact with agents that are computationally much weaker, for example when they work alongside humans or operate in complex environments where some tasks are handled by algorithms, heuristics, or other entities of varying computational power. For AI agents to successfully interact in these settings, however, achieving superhuman performance alone is not sufficient; they also need to account for suboptimal actions or idiosyncratic style from their less-skilled counterparts. We propose a formal evaluation framework for assessing the compatibility of near-optimal AI with interaction partners who may have much lower levels of skill; we use popular collaborative chess variants as model systems to study and develop AI agents that can successfully interact with lower-skill entities. Traditional chess engines designed to output near-optimal moves prove to be inadequate partners when paired with engines of various lower skill levels in this domain, as they are not designed to consider the presence of other agents. We contribute three methodologies to explicitly create skill-compatible AI agents in complex decision-making settings, and two chess game frameworks designed to foster collaboration between powerful AI agents and less-skilled partners. On these frameworks, our agents outperform state-of-the-art chess AI (based on AlphaZero) despite being weaker in conventional chess, demonstrating that skill-compatibility is a tangible trait that is qualitatively and measurably distinct from raw performance. Our evaluations further explore and clarify the mechanisms by which our agents achieve skill-compatibility.

This paper describes MAIA, a Multimodal Automated Interpretability Agent. MAIA is a system that uses neural models to automate neural model understanding tasks like feature interpretation and failure mode discovery. It equips a pre-trained vision-language model with a set of tools that support iterative experimentation on subcomponents of other models to explain their behavior. These include tools commonly used by human interpretability researchers: for synthesizing and editing inputs, computing maximally activating exemplars from real-world datasets, and summarizing and describing experimental results. Interpretability experiments proposed by MAIA compose these tools to describe and explain system behavior. We evaluate applications of MAIA to computer vision models. We first characterize MAIA's ability to describe (neuron-level) features in learned representations of images. Across several trained models and a novel dataset of synthetic vision neurons with paired ground-truth descriptions, MAIA produces descriptions comparable to those generated by expert human experimenters. We then show that MAIA can aid in two additional interpretability tasks: reducing sensitivity to spurious features, and automatically identifying inputs likely to be mis-classified.

Way back in 1985, a team of researchers at Carnegie Mellon University developed a computer purely to play games of chess. After moving to IBM, the computer was further developed, culminating in the obvious test – a match against then-world champion Garry Kasparov. However, the computer known as Deep Blue at this point wasn't enough for Kasparov; it lost four games to two. But like any good underdog, the computer was down but not out. It came back a year later to beat Kasparov in a narrow victory, winning by a single game.

World's only artificial intelligence program that makes mistakes on purpose. Artificial intelligence is known for being accurate, leaving no room for error. But one artificial intelligence program is taking the road untouched, making errors on purpose. This AI program is called Maia. Maia is a chess program that uses cutting-edge AI from the best chess-playing programs.

If you're in a household with teenage video game players, you will know the sound of Twitch streamers and YouTubers. Right now, my sons seem to live on a steady media diet of wildly enthusiastic young men, playing the same games, in the same ways, using the same slang. Over lockdown I have heard the words "What's up?" and "like and subscribe" enough times to last me until the heat death of the universe. Last weekend, my wife emerged from my youngest son's bedroom and said to me, between clenched teeth: "Is there no one different for them to watch?" And true, from the outside, game streaming can seem like a monoculture, dominated by energy drink-sponsored dudebros.

Artificial intelligence is known for being accurate, leaving no room for error. But one artificial intelligence program is taking the road untouched, making errors on purpose. This AI program is called Maia. Maia is a chess program that uses cutting-edge AI from the best chess-playing programs. But instead of being the grandmaster of chess and making every move right, Maia aims to predict human moves, even the wrong ones.