Related papers: Multi-metrics adaptively identifies backdoors in F…

Federated learning (FL), which aims to facilitate data collaboration across multiple organizations without exposing data privacy, encounters potential security risks. One serious threat is backdoor attacks, where an attacker injects a…

Deep neural networks are known to be vulnerable to adversarial perturbations, which are small and carefully crafted inputs that lead to incorrect predictions. In this paper, we propose DeepDefense, a novel defense framework that applies…

The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.…

Model pruning has gained traction as a promising defense strategy against backdoor attacks in deep learning. However, existing pruning-based approaches often fall short in accurately identifying and removing the specific parameters…

Model providers increasingly release open weights or allow users to fine-tune foundation models through APIs. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tuning on harmful data.…

Federated learning (FL) enables collaborative model training without sharing raw data but is vulnerable to gradient inversion attacks (GIAs), where adversaries reconstruct private data from shared gradients. Existing defenses either incur…

Federated Learning (FL) is a widely adopted privacy-preserving machine learning approach where private data remains local, enabling secure computations and the exchange of local model gradients between local clients and third-party…

Federated learning is considered as an effective privacy-preserving learning mechanism that separates the client's data and model training process. However, federated learning is still under the risk of privacy leakage because of the…

Recently, researchers have successfully employed Graph Neural Networks (GNNs) to build enhanced recommender systems due to their capability to learn patterns from the interaction between involved entities. In addition, previous studies have…

Deep Learning-based image synthesis techniques have been applied in healthcare research for generating medical images to support open research and augment medical datasets. Training generative adversarial neural networks (GANs) usually…

Federated learning (FL) has emerged as a transformative framework for privacy-preserving distributed training, allowing clients to collaboratively train a global model without sharing their local data. This is especially crucial in…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Federated Learning is a privacy preserving decentralized machine learning paradigm designed to collaboratively train models across multiple clients by exchanging gradients to the server and keeping private data local. Nevertheless, recent…

Backdoor attacks can implant malicious behaviours into deep models while preserving performance on clean data, posing a serious threat to safety-critical vision systems. Although backdoor mitigation has been studied extensively for image…

Federated Learning (FL) is a collaborative machine learning technique where multiple clients work together with a central server to train a global model without sharing their private data. However, the distribution shift across non-IID…

Most existing methods to detect backdoored machine learning (ML) models take one of the two approaches: trigger inversion (aka. reverse engineer) and weight analysis (aka. model diagnosis). In particular, the gradient-based trigger…

Backdoor attacks pose a significant threat to deep neural networks, particularly as recent advancements have led to increasingly subtle implantation, making the defense more challenging. Existing defense mechanisms typically rely on an…

Defending backdoor attacks in Federated Learning (FL) under heterogeneous client data distributions encounters limitations balancing effectiveness and privacy-preserving, while most existing methods highly rely on the assumption of…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Over-the-air federated learning (OTA-FL) improves communication efficiency by exploiting the superposition property of wireless channels, but this same property also creates a critical security vulnerability: the parameter server (PS)…