Pros and cons of GAN evaluation measures: New developments
A Borji - Computer Vision and Image Understanding, 2022 - Elsevier
This work is an update of my previous paper on the same topic published a few years ago
(Borji, 2019). With the dramatic progress in generative modeling, a suite of new quantitative …
(Borji, 2019). With the dramatic progress in generative modeling, a suite of new quantitative …
Extracting training data from diffusion models
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion have attracted
significant attention due to their ability to generate high-quality synthetic images. In this work …
significant attention due to their ability to generate high-quality synthetic images. In this work …
Enhanced membership inference attacks against machine learning models
J Ye, A Maddi, SK Murakonda… - Proceedings of the …, 2022 - dl.acm.org
How much does a machine learning algorithm leak about its training data, and why?
Membership inference attacks are used as an auditing tool to quantify this leakage. In this …
Membership inference attacks are used as an auditing tool to quantify this leakage. In this …
Structure-informed language models are protein designers
This paper demonstrates that language models are strong structure-based protein
designers. We present LM-Design, a generic approach to reprogramming sequence-based …
designers. We present LM-Design, a generic approach to reprogramming sequence-based …
Training data influence analysis and estimation: A survey
Z Hammoudeh, D Lowd - Machine Learning, 2024 - Springer
Good models require good training data. For overparameterized deep models, the causal
relationship between training data and model predictions is increasingly opaque and poorly …
relationship between training data and model predictions is increasingly opaque and poorly …
Training data extraction from pre-trained language models: A survey
S Ishihara - arXiv preprint arXiv:2305.16157, 2023 - arxiv.org
As the deployment of pre-trained language models (PLMs) expands, pressing security
concerns have arisen regarding the potential for malicious extraction of training data, posing …
concerns have arisen regarding the potential for malicious extraction of training data, posing …
Practical membership inference attacks against fine-tuned large language models via self-prompt calibration
Membership Inference Attacks (MIA) aim to infer whether a target data record has been
utilized for model training or not. Prior attempts have quantified the privacy risks of language …
utilized for model training or not. Prior attempts have quantified the privacy risks of language …
Feature likelihood score: Evaluating the generalization of generative models using samples
The past few years have seen impressive progress in the development of deep generative
models capable of producing high-dimensional, complex, and photo-realistic data. However …
models capable of producing high-dimensional, complex, and photo-realistic data. However …
Generating realistic neurophysiological time series with denoising diffusion probabilistic models
Denoising diffusion probabilistic models (DDPMs) have recently been shown to accurately
generate complicated data such as images, audio, or time series. Experimental and clinical …
generate complicated data such as images, audio, or time series. Experimental and clinical …
Diffusion probabilistic models generalize when they fail to memorize
In this work, we study the training of diffusion probabilistic models through a series of
hypotheses and carefully designed experiments. We call our key finding the memorization …
hypotheses and carefully designed experiments. We call our key finding the memorization …