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 …

Good models require good training data. For overparameterized deep models, the causal
relationship between training data and model predictions is increasingly opaque and poorly …

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 …

Traditional unlearnable strategies have been proposed to prevent unauthorized users from
training on the 2D image data. With more 3D point cloud data containing sensitivity …

As the curation of data for machine learning becomes increasingly automated, dataset
tampering is a mounting threat. Backdoor attackers tamper with training data to embed a …

Data Poisoning Attacks (DPA) represent a sophisticated technique aimed at distorting the
training data of machine learning models, thereby manipulating their behavior. This process …

The tremendous amount of accessible data in cyberspace face the risk of being
unauthorized used for training deep learning models. To address this concern, methods are …

Large-scale training of modern deep learning models heavily relies on publicly available
data on the web. This potentially unauthorized usage of online data leads to concerns …

Perturbative availability poisoning (PAP) adds small changes to images to prevent their use
for model training. Current research adopts the belief that practical and effective approaches …