Trojvit: Trojan insertion in vision transformers

M Zheng, Q Lou, L Jiang - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Abstract Vision Transformers (ViTs) have demonstrated the state-of-the-art performance in
various vision-related tasks. The success of ViTs motivates adversaries to perform backdoor …

A Comprehensive Survey on Backdoor Attacks and their Defenses in Face Recognition Systems

Q Le Roux, E Bourbao, Y Teglia, K Kallas - IEEE Access, 2024 - ieeexplore.ieee.org
Deep learning has significantly transformed face recognition, enabling the deployment of
large-scale, state-of-the-art solutions worldwide. However, the widespread adoption of deep …

A dual stealthy backdoor: From both spatial and frequency perspectives

Y Gao, H Chen, P Sun, J Li, A Zhang, Z Wang… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Backdoor attacks pose serious security threats to deep neural networks (DNNs).
Backdoored models make arbitrarily (targeted) incorrect predictions on inputs containing …

MBA: Backdoor Attacks Against 3D Mesh Classifier

L Fan, F He, T Si, R Fan, C Ye… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
3D mesh classification deep neural network (3D DNN) has been widely applied in many
safety-critical domains. Backdoor attack is a serious threat that occurs during the training …

Look, listen, and attack: Backdoor attacks against video action recognition

HAAK Hammoud, S Liu, M Alkhrashi… - 2024 IEEE/CVF …, 2024 - ieeexplore.ieee.org
Deep neural networks (DNNs) are vulnerable to a class of attacks called" backdoor attacks",
which create an association between a backdoor trigger and a target label the attacker is …

Look Listen and Attack: Backdoor Attacks Against Video Action Recognition

HA Al Kader Hammoud, S Liu… - Proceedings of the …, 2024 - openaccess.thecvf.com
Deep neural networks (DNNs) are vulnerable to a class of attacks called" backdoor attacks".
which create an association between a backdoor trigger and a target label the attacker is …

M-to-N Backdoor Paradigm: A Multi-Trigger and Multi-Target Attack to Deep Learning Models

L Hou, Z Hua, Y Li, Y Zheng… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where a backdoored
model behaves normally with clean inputs but exhibits attacker-specified behaviors upon the …

Untargeted backdoor attack against deep neural networks with imperceptible trigger

M Xue, Y Wu, S Ni, LY Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Recent research works have demonstrated that deep neural networks (DNNs) are
vulnerable to backdoor attacks. The existing backdoor attacks can only cause targeted …

Attacks in adversarial machine learning: A systematic survey from the life-cycle perspective

B Wu, Z Zhu, L Liu, Q Liu, Z He, S Lyu - arXiv preprint arXiv:2302.09457, 2023 - arxiv.org
Adversarial machine learning (AML) studies the adversarial phenomenon of machine
learning, which may make inconsistent or unexpected predictions with humans. Some …

The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data

Z Zhu, R Wang, C Zou, L Jing - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Recently, backdoor attacks have posed a serious security threat to the training process of
deep neural networks (DNNs). The attacked model behaves normally on benign samples …