Federated learning has emerged as a promising paradigm for privacy-preserving
collaboration among different parties. Recently, with the popularity of federated learning, an …

Recently, various parameter-efficient fine-tuning (PEFT) strategies for application to
language models have been proposed and successfully implemented. However, this raises …

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

Recent research findings suggest that machine learning models are highly susceptible to
backdoor poisoning attacks. Backdoor poisoning attacks can be easily executed and …

Diffusion Models are vulnerable to backdoor attacks, where malicious attackers inject
backdoors by poisoning some parts of the training samples during the training stage. This …

Recent studies have revealed the vulnerability of deep neural networks (DNNs) to various
backdoor attacks, where the behavior of DNNs can be compromised by utilizing certain …

Studies on backdoor attacks in recent years suggest that an adversary can compromise the
integrity of a deep neural network (DNN) by manipulating a small set of training samples …

We propose a Universal Defence against backdoor attacks based on Clustering and
Centroids Analysis (CCA-UD). The goal of the defence is to reveal whether a Deep Neural …

A backdoored deep hashing model is expected to behave normally on original query
images and return the images with the target label when a specific trigger pattern presents …

Untrusted data used to train a model might have been manipulated to endow the learned
model with hidden properties that the data contributor might later exploit. Data purification …