The success of machine learning is fueled by the increasing availability of computing power
and large training datasets. The training data is used to learn new models or update existing …

Speech-centric machine learning systems have revolutionized a number of leading
industries ranging from transportation and healthcare to education and defense …

Deep learning models are often trained on distributed, web-scale datasets crawled from the
internet. In this paper, we introduce two new dataset poisoning attacks that intentionally …

Instruction tuning is an effective technique to align large language models (LLMs) with
human intent. In this work, we investigate how an adversary can exploit instruction tuning by …

Backdoor attack intends to embed hidden backdoors into deep neural networks (DNNs), so
that the attacked models perform well on benign samples, whereas their predictions will be …

The prosperity of deep neural networks (DNNs) is largely benefited from open-source
datasets, based on which users can evaluate and improve their methods. In this paper, we …

In a backdoor attack, an adversary injects corrupted data into a model's training dataset in
order to gain control over its predictions on images with a specific attacker-defined trigger. A …

Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the
rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets …

Recent trends in language modeling have focused on increasing performance through
scaling, and have resulted in an environment where training language models is out of …

As machine learning systems grow in scale, so do their training data requirements, forcing
practitioners to automate and outsource the curation of training data in order to achieve state …