M Xu, S Yoon, A Fuentes, DS Park - Pattern Recognition, 2023 - Elsevier
Although deep learning has achieved satisfactory performance in computer vision, a large volume of images is required. However, collecting images is often expensive and …
In tasks involving the interpretation of medical images, suitably trained machine-learning models often exceed the performance of medical experts. Yet such a high-level of …
It has been recognized that the data generated by the denoising diffusion probabilistic model (DDPM) improves adversarial training. After two years of rapid development in …
Motivated by concerns that large-scale diffusion models can produce undesirable output such as sexually explicit content or copyrighted artistic styles, we study erasure of specific …
Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This …
Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama …
N Carlini, S Chien, M Nasr, S Song… - … IEEE Symposium on …, 2022 - ieeexplore.ieee.org
A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training …
A Zhang, L Xing, J Zou, JC Wu - Nature Biomedical Engineering, 2022 - nature.com
In the past decade, the application of machine learning (ML) to healthcare has helped drive the automation of physician tasks as well as enhancements in clinical capabilities and …
We present modality gap, an intriguing geometric phenomenon of the representation space of multi-modal models. Specifically, we show that different data modalities (eg images and …