Christopher A. Choquette-Choo

TL;DR: Label-only membership inference attacks as mentioned in this paper evaluate the robustness of a model's predicted labels under perturbations to obtain a fine-grained membership signal, and empirically show that label-only attacks perform on par with prior attacks that required access to model confidences.

TL;DR: SISA training as mentioned in this paper is a framework that expedites the unlearning process by strategically limiting the influence of a data point in the training procedure, and it is designed to achieve the largest improvements for stateful algorithms like stochastic gradient descent for deep neural networks.

TL;DR: Entangled Watermarking Embeddings (EWE) is introduced, which encourages the model to learn common features for classifying data that is sampled from the task distribution, but also data that encodes watermarks, which forces an adversary attempting to remove watermarks that are entangled with legitimate data to sacrifice performance on legitimate data.

TL;DR: The PaLM 2 model as mentioned in this paper is a Transformer-based model trained using a mixture of objectives, which has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM.

TL;DR: In this paper, the authors introduce the concept of proof-of-learning in machine learning and demonstrate how a seminal training algorithm accumulates secret information due to its stochasticity.