In recent years, diffusion models [1, 2], particularly latent diffusion models [3], have spearheaded high quality textto-image generation, and have been widely adopted by researchers and the general public alike. Trained on massive datasets like LAION-5B [4], these models have developed a broad understanding of visual concepts, enabling new creative and practical applications. Notably, tools like Stable Diffusion [3, 5] have been made readily accessible for general use. Building on this foundation, efficient adaptation methods such as parameter efficient fine-tuning (PEFT) [6, 7, 8], guidance based approaches [9, 10, 11], and pseudo-word generation [12] enable users to leverage this extensive pretraining for customizing models that can specialize on downstream tasks with smaller datasets. However, the rapid adoption of diffusion models has also raised significant privacy, ethical and legal concerns. One critical issue is the vulnerability of these models to privacy attacks, from membership inference [13], where an attacker determines whether a specific data point was used to train a particular model, to data extraction [14], which enables an attacker to reconstruct particular images from the training dataset. This issue is even more severe during the fine-tuning phase where the model is fine-tuned on smaller specialized datasets from a possibly different domain and each data record has more impact on the final model. This risk underscores the importance of privacy-preserving technologies, particularly as diffusion models often rely on vast datasets scraped from the internet without explicit consent from content owners.

Recent literature has demonstrated the difficulty of classifying between composers who write in extremely similar styles (homogeneous style). Additionally, machine learning studies in this field have been exclusively of technical import with little musicological interpretability or significance. We present a supervised machine learning system which addresses the difficulty of differentiating between stylistically homogeneous composers using foundational elements of music, their complexity and interaction. Our work expands on previous style classification studies by developing more complex features as well as introducing a new class of musical features which focus on local irregularities within musical scores. We demonstrate the discriminative power of the system as applied to Haydn and Mozart's string quartets. Our results yield interpretable musicological conclusions about Haydn's and Mozart's stylistic differences while distinguishing between the composers with higher accuracy than previous studies in this domain.

User-Centered Programming by Demonstration is an approach that places the needs of people above algorithmic constraints and requirements. In this paper we present a user-centered programming by demonstration project for authoring interactive robotic locomotion style. The style in which a robot moves about a space, expressed through its motions, can be used for communication. For example, a robot could move aggressively in reaction to a person’s actions, or alternatively react using careful, submissive movements. We present a new demonstration interface, algorithm, and evaluation results.