A survey of backdoor attacks and defences: From deep neural networks to large language models

A survey of backdoor attacks and defences: From deep neural networks to large language models

Deep neural networks (DNNs) have found extensive applications in safety-critical artificial intelligence systems, such as autonomous driving and facial recognition systems. However, recent research has revealed their susceptibility to backdoors maliciously injected by adversaries. This vulnerability...

Full description

Saved in:

Bibliographic Details
Main Authors:	Ling-Xin Jin, Wei Jiang, Xiang-Yu Wen, Mei-Yu Lin, Jin-Yu Zhan, Xing-Zhi Zhou, Maregu Assefa Habtie, Naoufel Werghi
Format:	Article
Language:	English
Published:	KeAi Communications Co., Ltd. 2025-09-01
Series:	Journal of Electronic Science and Technology
Subjects:	Backdoor attacks Backdoor defenses Deep neural networks Large language model
Online Access:	http://www.sciencedirect.com/science/article/pii/S1674862X25000278
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Method for Robust Backdoor Detection and Removal in Feature Space Using Clean Data
by: Donik Vrsnak, et al.
Published: (2025-01-01)

A4FL: Federated Adversarial Defense via Adversarial Training and Pruning Against Backdoor Attack
by: Saeed-Uz-Zaman, et al.
Published: (2025-01-01)

Backdoor defense method in federated learning based on contrastive training
by: Jiale ZHANG, et al.
Published: (2024-03-01)

Survey on Backdoor Attacks on Deep Learning: Current Trends, Categorization, Applications, Research Challenges, and Future Prospects
by: Muhammad Abdullah Hanif, et al.
Published: (2025-01-01)

CLB-Defense: based on contrastive learning defense for graph neural network against backdoor attack
by: Jinyin CHEN, et al.
Published: (2023-04-01)

Defending Deep Neural Networks Against Backdoor Attack by Using De-Trigger Autoencoder
by: Hyun Kwon
Published: (2025-01-01)

A Backdoor Approach With Inverted Labels Using Dirty Label-Flipping Attacks
by: Orson Mengara
Published: (2025-01-01)

A sparse and invisible targeted backdoor attack in federated learning
by: Qikun Zhang, et al.
Published: (2025-07-01)

A Backdoor Attack Against LSTM-Based Text Classification Systems
by: Jiazhu Dai, et al.
Published: (2019-01-01)

Clean-label backdoor attack on link prediction task
by: Junming Mo, et al.
Published: (2025-08-01)

FLARE: A Backdoor Attack to Federated Learning with Refined Evasion
by: Qingya Wang, et al.
Published: (2024-11-01)

Text Select-Backdoor: Selective Backdoor Attack for Text Recognition Systems
by: Hyun Kwon, et al.
Published: (2024-01-01)

Backdoor Attack to Giant Model in Fragment-Sharing Federated Learning
by: Senmao Qi, et al.
Published: (2024-12-01)

BDEKD: mitigating backdoor attacks in NLP models via ensemble knowledge distillation
by: Zijie Zhang, et al.
Published: (2025-07-01)

Towards Robust Speech Models: Mitigating Backdoor Attacks via Audio Signal Enhancement and Fine-Pruning Techniques
by: Heyan Sun, et al.
Published: (2025-03-01)

Stealthy graph backdoor attack based on feature trigger
by: Yang Chen, et al.
Published: (2025-06-01)

Backdoor Defence for Voice Print Recognition Model Based on Speech Enhancement and Weight Pruning
by: Jiawei Zhu, et al.
Published: (2022-01-01)

Natural Occlusion-Based Backdoor Attacks: A Novel Approach to Compromising Pedestrian Detectors
by: Qiong Li, et al.
Published: (2025-07-01)

Effective defense against physically embedded backdoor attacks via clustering-based filtering
by: Mohammed Kutbi
Published: (2025-04-01)

Multi-Targeted Textual Backdoor Attack: Model-Specific Misrecognition via Trigger Position and Word Choice
by: Taehwa Lee, et al.
Published: (2025-01-01)

CleanSheet: Advancing backdoor attack techniques for deep neural networks with stealthy trigger embedding
by: Ahmed Bensaoud, et al.
Published: (2025-12-01)

Backdoor Attack Based on Lossy Image Compression Using Discrete Cosine Transform
by: Yuting Liu, et al.
Published: (2024-01-01)

Backdoor Attack Against Dataset Distillation in Natural Language Processing
by: Yuhao Chen, et al.
Published: (2024-12-01)

Data Poisoning Attack on Black-Box Neural Machine Translation to Truncate Translation
by: Lingfang Li, et al.
Published: (2024-12-01)

Adversarial Training for Mitigating Insider-Driven XAI-Based Backdoor Attacks
by: R. G. Gayathri, et al.
Published: (2025-05-01)

Detecting All-to-One Backdoor Attacks in Black-Box DNNs via Differential Robustness to Noise
by: Hao Fu, et al.
Published: (2025-01-01)

EarlyExodus: Leveraging early exits to mitigate backdoor vulnerability in deep learning
by: Salmane Douch, et al.
Published: (2025-09-01)

A Novel and Efficient Multi-Target Backdoor Attack for Deep Learning-Based Wireless Signal Classifiers
by: Nayan Moni Baishya, et al.
Published: (2025-01-01)

Improved Distributed Backdoor Attacks in Federated Learning by Density-Adaptive Data Poisoning and Projection-Based Gradient Updating
by: Jian Wang, et al.
Published: (2025-01-01)

TIBW: Task-Independent Backdoor Watermarking with Fine-Tuning Resilience for Pre-Trained Language Models
by: Weichuan Mo, et al.
Published: (2025-01-01)

Survey on vertical federated learning: algorithm, privacy and security
by: Jinyin CHEN, et al.
Published: (2023-04-01)

Hard-coded backdoor detection method based on semantic conflict
by: Anxiang HU, et al.
Published: (2023-02-01)

Backdoor detection in embedded system firmware without file system
by: Chao-jian HU, et al.
Published: (2013-08-01)

GuardianMPC: Backdoor-Resilient Neural Network Computation
by: Mohammad Hashemi, et al.
Published: (2025-01-01)

Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery
by: Ching-Chun Chang, et al.
Published: (2025-01-01)

Enhancing Security in International Data Spaces: A STRIDE Framework Approach
by: Nikola Gavric, et al.
Published: (2024-12-01)

Causal ECGNet: leveraging causal inference for robust ECG classification in cardiac disorders
by: Mei Wang, et al.
Published: (2025-05-01)

Quantitative method for network security situation based on attack prediction
by: Hao HU, et al.
Published: (2017-10-01)

Quantitative method for network security situation based on attack prediction
by: Hao HU, et al.
Published: (2017-10-01)

A Comprehensive Review of Adversarial Attacks and Defense Strategies in Deep Neural Networks
by: Abdulruhman Abomakhelb, et al.
Published: (2025-05-01)