This work provides the community with a timely comprehensive review of backdoor attacks
and countermeasures on deep learning. According to the attacker's capability and affected …

AI has provided us with the ability to automate tasks, extract information from vast amounts of
data, and synthesize media that is nearly indistinguishable from the real thing. However …

Machine learning (ML) systems are rapidly increasing in size, are acquiring new
capabilities, and are increasingly deployed in high-stakes settings. As with other powerful …

Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

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 …

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 …

Backdoor learning is an emerging and vital topic for studying deep neural networks'
vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being …

Self-supervised learning in computer vision aims to pre-train an image encoder using a
large amount of unlabeled images or (image, text) pairs. The pre-trained image encoder can …

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 …

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 …