Due to the greatly improved capabilities of devices, massive data, and increasing concern
about data privacy, Federated Learning (FL) has been increasingly considered for …

Abstract Vision Transformers (ViTs), which made a splash in the field of computer vision
(CV), have shaken the dominance of convolutional neural networks (CNNs). However, in the …

Due to the increasing computational demand of Deep Neural Networks (DNNs), companies
and organizations have begun to outsource the training process. However, the externally …

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural
Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of …

In light of their remarkable predictive capabilities, artificial intelligence (AI) models driven by
deep learning (DL) have witnessed widespread adoption in the agriculture sector …

This paper proposes a simple method to distill and detect backdoor patterns within an
image:\emph {Cognitive Distillation}(CD). The idea is to extract the" minimal essence" from …

Backdoor attacks have emerged as one of the major security threats to deep learning
models as they can easily control the model's test-time predictions by pre-injecting a …

Backdoor attacks have been well-studied in visible light object detection (VLOD) in recent
years. However VLOD can not effectively work in dark and temperature-sensitive scenarios …

Object detection using deep learning has attracted considerable interest from researchers
because of its competency in performing state-of-the-art tasks, including detection …

The paper addresses the challenging problem of counting objects or entities in an image
without relying on specific category information, known as class-agnostic counting (CAC) …