The prosperity of machine learning has been accompanied by increasing attacks on the
training process. Among them, poisoning attacks have become an emerging threat during …

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 …

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 …

Data-centric AI is at the center of a fundamental shift in software engineering where machine
learning becomes the new software, powered by big data and computing infrastructure …

Backdoor attack has emerged as a major security threat to deep neural networks (DNNs).
While existing defense methods have demonstrated promising results on detecting or …

Recently, machine learning models have demonstrated to be vulnerable to backdoor
attacks, primarily due to the lack of transparency in black-box models such as deep neural …

Trained on billions of images, diffusion-based text-to-image models seem impervious to
traditional data poisoning attacks, which typically require poison samples approaching 20 …

Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep
neural networks in which participants' data remains on their own devices with only model …

With the success of deep learning algorithms in various domains, studying adversarial
attacks to secure deep models in real world applications has become an important research …

We introduce a new class of attacks on machine learning models. We show that an
adversary who can poison a training dataset can cause models trained on this dataset to …