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 …

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 …

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 …

Although backdoor learning is an active research topic in the NLP domain, the literature
lacks studies that systematically categorize and summarize backdoor attacks and defenses …

Self-supervised learning is an emerging machine learning (ML) paradigm. Compared to
supervised learning which leverages high-quality labeled datasets, self-supervised learning …

An off-the-shelf model as a commercial service could be stolen by model stealing attacks,
posing great threats to the rights of the model owner. Model fingerprinting aims to verify …

Deep learning has significantly transformed face recognition, enabling the deployment of
large-scale, state-of-the-art solutions worldwide. However, the widespread adoption of deep …

Pre-trained vision models (PVMs) have become a dominant component due to their
exceptional performance when fine-tuned for downstream tasks. However, the presence of …

Modern autonomous vehicles adopt state-of-the-art DNN models to interpret the sensor data
and perceive the environment. However, DNN models are vulnerable to different types of …

Recent works have revealed the vulnerability of deep neural networks to backdoor attacks,
where a backdoored model orchestrates targeted or untargeted misclassification when …