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

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 …

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 …

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

Abstract Contrastive Vision-Language Pre-training known as CLIP has shown promising
effectiveness in addressing downstream image recognition tasks. However recent works …

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 …

In the field of natural language processing, the prevalent approach involves fine-tuning
pretrained language models (PLMs) using local samples. Recent research has exposed the …

Recent studies revealed that using third-party models may lead to backdoor threats, where
adversaries can maliciously manipulate model predictions based on backdoors implanted …

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 …

Large Language Models (LLMs), such as LLaMA and GPT-4, have transformed the
paradigm of natural language comprehension and generation. Despite their impressive …