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 last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …

Artificial Intelligence (AI) relies heavily on deep learning-a technology that is becoming
increasingly popular in real-life applications of AI, even in the safety-critical and high-risk …

Topological deep learning (TDL) is a rapidly evolving field that uses topological features to
understand and design deep learning models. This paper posits that TDL may complement …

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against
prompt-based models consider injecting backdoors into the entire embedding layers or word …

Recent studies have revealed that\textit {Backdoor Attacks} can threaten the safety of natural
language processing (NLP) models. Investigating the strategies of backdoor attacks will help …

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data
poisoning backdoor attacks. It was shown that an adversary can poison a small part of the …

Trojan attacks raise serious security concerns. In this paper, we investigate the underlying
mechanism of Trojaned BERT models. We observe the attention focus drifting behavior of …

Adversarial phenomenon has been widely observed in machine learning (ML) systems,
especially in those using deep neural networks, describing that ML systems may produce …

Deep Learning-based image synthesis techniques have been applied in healthcare
research for generating medical images to support open research and augment medical …