Backdoor learning: A survey

Y Li, Y Jiang, Z Li, ST **a - IEEE Transactions on Neural …, 2022‏ - ieeexplore.ieee.org
Backdoor attack intends to embed hidden backdoors into deep neural networks (DNNs), so
that the attacked models perform well on benign samples, whereas their predictions will be …

Narcissus: A practical clean-label backdoor attack with limited information

Y Zeng, M Pan, HA Just, L Lyu, M Qiu… - Proceedings of the 2023 …, 2023‏ - dl.acm.org
Backdoor attacks introduce manipulated data into a machine learning model's training set,
causing the model to misclassify inputs with a trigger during testing to achieve a desired …

Revisiting the assumption of latent separability for backdoor defenses

X Qi, T **e, Y Li, S Mahloujifar… - The eleventh international …, 2023‏ - openreview.net
Recent studies revealed that deep learning is susceptible to backdoor poisoning attacks. An
adversary can embed a hidden backdoor into a model to manipulate its predictions by only …

Badchain: Backdoor chain-of-thought prompting for large language models

Z **ang, F Jiang, Z **ong, B Ramasubramanian… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting,
particularly when tackling tasks that require systematic reasoning processes. On the other …

Clean-image backdoor: Attacking multi-label models with poisoned labels only

K Chen, X Lou, G Xu, J Li, T Zhang - The Eleventh International …, 2022‏ - openreview.net
Multi-label models have been widely used in various applications including image
annotation and object detection. The fly in the ointment is its inherent vulnerability to …

Towards a proactive {ML} approach for detecting backdoor poison samples

X Qi, T **e, JT Wang, T Wu, S Mahloujifar… - 32nd USENIX Security …, 2023‏ - usenix.org
Adversaries can embed backdoors in deep learning models by introducing backdoor poison
samples into training datasets. In this work, we investigate how to detect such poison …

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 …

Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunities

S Neupane, S Mitra, IA Fernandez, S Saha… - IEEE …, 2024‏ - ieeexplore.ieee.org
Robotics and Artificial Intelligence (AI) have been inextricably intertwined since their
inception. Today, AI-Robotics systems have become an integral part of our daily lives, from …

Backdoor attacks to deep learning models and countermeasures: A survey

Y Li, S Zhang, W Wang, H Song - IEEE Open Journal of the …, 2023‏ - ieeexplore.ieee.org
Backdoor attacks have severely threatened deep neural network (DNN) models in the past
several years. In backdoor attacks, the attackers try to plant hidden backdoors into DNN …

LoneNeuron: a highly-effective feature-domain neural trojan using invisible and polymorphic watermarks

Z Liu, F Li, Z Li, B Luo - Proceedings of the 2022 ACM SIGSAC …, 2022‏ - dl.acm.org
The wide adoption of deep neural networks (DNNs) in real-world applications raises
increasing security concerns. Neural Trojans embedded in pre-trained neural networks are …