A comprehensive survey on poisoning attacks and countermeasures in machine learning

Z Tian, L Cui, J Liang, S Yu - ACM Computing Surveys, 2022‏ - dl.acm.org
The prosperity of machine learning has been accompanied by increasing attacks on the
training process. Among them, poisoning attacks have become an emerging threat during …

Wild patterns reloaded: A survey of machine learning security against training data poisoning

AE Cinà, K Grosse, A Demontis, S Vascon… - ACM Computing …, 2023‏ - dl.acm.org
The success of machine learning is fueled by the increasing availability of computing power
and large training datasets. The training data is used to learn new models or update existing …

Anti-backdoor learning: Training clean models on poisoned data

Y Li, X Lyu, N Koren, L Lyu, B Li… - Advances in Neural …, 2021‏ - proceedings.neurips.cc
Backdoor attack has emerged as a major security threat to deep neural networks (DNNs).
While existing defense methods have demonstrated promising results on detecting or …

Invisible backdoor attack with sample-specific triggers

Y Li, Y Li, B Wu, L Li, R He… - Proceedings of the IEEE …, 2021‏ - openaccess.thecvf.com
Recently, backdoor attacks pose a new security threat to the training process of deep neural
networks (DNNs). Attackers intend to inject hidden backdoors into DNNs, such that the …

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 …

“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 …

Detecting backdoors in pre-trained encoders

S Feng, G Tao, S Cheng, G Shen… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Self-supervised learning in computer vision trains on unlabeled data, such as images or
(image, text) pairs, to obtain an image encoder that learns high-quality embeddings for input …

Bppattack: Stealthy and efficient trojan attacks against deep neural networks via image quantization and contrastive adversarial learning

Z Wang, J Zhai, S Ma - … of the IEEE/CVF conference on …, 2022‏ - openaccess.thecvf.com
Deep neural networks are vulnerable to Trojan attacks. Existing attacks use visible patterns
(eg, a patch or image transformations) as triggers, which are vulnerable to human …

Blind backdoors in deep learning models

E Bagdasaryan, V Shmatikov - 30th USENIX Security Symposium …, 2021‏ - usenix.org
We investigate a new method for injecting backdoors into machine learning models, based
on compromising the loss-value computation in the model-training code. We use it to …

Hidden trigger backdoor attack on {NLP} models via linguistic style manipulation

X Pan, M Zhang, B Sheng, J Zhu, M Yang - 31st USENIX Security …, 2022‏ - usenix.org
The vulnerability of deep neural networks (DNN) to backdoor (trojan) attacks is extensively
studied for the image domain. In a backdoor attack, a DNN is modified to exhibit expected …