The prosperity of deep neural networks (DNNs) is largely benefited from open-source
datasets, based on which users can evaluate and improve their methods. In this paper, we …

Backdoor defenses have been studied to alleviate the threat of deep neural networks
(DNNs) being backdoor attacked and thus maliciously altered. Since DNNs usually adopt …

Recent studies demonstrated that deep neural networks (DNNs) are vulnerable to backdoor
attacks. The attacked model behaves normally on benign samples, while its predictions are …

Abstract Model quantization is widely used to compress and accelerate deep neural
networks. However recent studies have revealed the feasibility of weaponizing model …

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries
embed a hidden backdoor trigger during the training process for malicious prediction …

Deep learning, especially deep neural networks (DNNs), has been widely and successfully
adopted in many critical applications for its high effectiveness and efficiency. The rapid …

Backdoor attacks inject poisoned samples into the training data, resulting in the
misclassification of the poisoned input during a model's deployment. Defending against …

Saliency-based representation visualization (SRV)($ eg $, Grad-CAM) is one of the most
classical and widely adopted explainable artificial intelligence (XAI) methods for its simplicity …

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats
when training with third-party resources (such as training samples or backbones). The back …

The field of few-shot learning (FSL) has shown promising results in scenarios where training
data is limited, but its vulnerability to backdoor attacks remains largely unexplored. We first …