Backdoor attacks and countermeasures on deep learning: A comprehensive review

Y Gao, BG Doan, Z Zhang, S Ma, J Zhang, A Fu… - arXiv preprint arXiv …, 2020 - arxiv.org
This work provides the community with a timely comprehensive review of backdoor attacks
and countermeasures on deep learning. According to the attacker's capability and affected …

Adversarial machine learning in image classification: A survey toward the defender's perspective

GR Machado, E Silva, RR Goldschmidt - ACM Computing Surveys …, 2021 - dl.acm.org
Deep Learning algorithms have achieved state-of-the-art performance for Image
Classification. For this reason, they have been used even in security-critical applications …

Adversarial neuron pruning purifies backdoored deep models

D Wu, Y Wang - Advances in Neural Information Processing …, 2021 - proceedings.neurips.cc
As deep neural networks (DNNs) are growing larger, their requirements for computational
resources become huge, which makes outsourcing training more popular. Training in a third …

Abs: Scanning neural networks for back-doors by artificial brain stimulation

Y Liu, WC Lee, G Tao, S Ma, Y Aafer… - Proceedings of the 2019 …, 2019 - dl.acm.org
This paper presents a technique to scan neural network based AI models to determine if
they are trojaned. Pre-trained AI models may contain back-doors that are injected through …

Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses

M Goldblum, D Tsipras, C Xie, X Chen… - … on Pattern Analysis …, 2022 - ieeexplore.ieee.org
As machine learning systems grow in scale, so do their training data requirements, forcing
practitioners to automate and outsource the curation of training data in order to achieve state …

Detecting ai trojans using meta neural analysis

X Xu, Q Wang, H Li, N Borisov… - 2021 IEEE Symposium …, 2021 - ieeexplore.ieee.org
In machine learning Trojan attacks, an adversary trains a corrupted model that obtains good
performance on normal data but behaves maliciously on data samples with certain trigger …

Better trigger inversion optimization in backdoor scanning

G Tao, G Shen, Y Liu, S An, Q Xu… - Proceedings of the …, 2022 - openaccess.thecvf.com
Backdoor attacks aim to cause misclassification of a subject model by stamping a trigger to
inputs. Backdoors could be injected through malicious training and naturally exist. Deriving …

Fakespotter: A simple yet robust baseline for spotting ai-synthesized fake faces

R Wang, F Juefei-Xu, L Ma, X Xie, Y Huang… - arXiv preprint arXiv …, 2019 - arxiv.org
In recent years, generative adversarial networks (GANs) and its variants have achieved
unprecedented success in image synthesis. They are widely adopted in synthesizing facial …

Backdoor attacks against deep learning systems in the physical world

E Wenger, J Passananti, AN Bhagoji… - Proceedings of the …, 2021 - openaccess.thecvf.com
Backdoor attacks embed hidden malicious behaviors into deep learning models, which only
activate and cause misclassifications on model inputs containing a specific" trigger." Existing …

“real attackers don't compute gradients”: bridging the gap between adversarial ml research and practice

G Apruzzese, HS Anderson, S Dambra… - … IEEE Conference on …, 2023 - ieeexplore.ieee.org
Recent years have seen a proliferation of research on adversarial machine learning.
Numerous papers demonstrate powerful algorithmic attacks against a wide variety of …