In this paper, we extend the study of concept ablation within pre-trained models as introduced in ‘Ablating Concepts in Text-to-Image Diffusion Models’. Our work focuses on reproducing the results achieved by the different variants of concept ablation proposed through predefined metrics. We also introduce a novel variant of concept ablation—trademark ablation. This variant combines the principles of memorization and instance ablation to tackle the nuanced influence of proprietary or branded elements in model outputs. Further, our research contributions include an observational analysis of the model’s limitations. Moreover, we investigate the model’s behavior in response to ablation leakage-inducing prompts, which aim to indirectly ablate concepts, revealing insights into the model’s resilience and adaptability. We also observe the model’s performance degradation on images generated by concepts far from its target ablation concept.

In this evolving era of machine learning security, membership inference attacks have emerged as a potent threat to the confidentiality of sensitive data. In this attack, adversaries aim to determine whether a particular point was used during the training of a target model. This paper proposes a new method to gauge a data point’s membership in a model’s training set. Instead of correlating loss with membership, as is traditionally done, we have leveraged the fact that training examples generally exhibit higher confidence values when classified into their actual class. During training, the model is essentially being ‘fit’ to the training data and might face particular difficulties in generalization to unseen data. This asymmetry leads to the model achieving higher confidence on the training data as it exploits the specific patterns and noise present in the training data. Our proposed approach leverages the confidence values generated by the machine learning model. These confidence values provide a probabilistic measure of the model’s certainty in its predictions and can further be used to infer the membership of a given data point. Additionally, we also introduce another variant of our method that allows us to carry out this attack without knowing the ground truth(true class) of a given data point, thus offering an edge over existing label-dependent attack methods.

Universal Image Segmentation is not a new concept. Past attempts to unify image segmentation in the last decades include scene parsing, panoptic segmentation, and, more recently, new panoptic architectures. We propose OneFormer, a universal image segmentation framework that unifies segmentation with a multi-task train-once design.

In this paper, we revisited the core design ideas of stateof-the-art deep inpainting networks. We propose an intuitive and effective inpainting architecture that augments the powerful comodulated StyleGAN2 generator with the high receptiveness ability of FFC to achieve equally good performance on both textures and structures.