Backdoor learning: A survey
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 …
that the attacked models perform well on benign samples, whereas their predictions will be …
Domain watermark: Effective and harmless dataset copyright protection is closed at hand
The prosperity of deep neural networks (DNNs) is largely benefited from open-source
datasets, based on which users can evaluate and improve their methods. In this paper, we …
datasets, based on which users can evaluate and improve their methods. In this paper, we …
Backdoor defense via decoupling the training process
Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor
attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few …
attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few …
Untargeted backdoor watermark: Towards harmless and stealthy dataset copyright protection
Y Li, Y Bai, Y Jiang, Y Yang… - Advances in Neural …, 2022 - proceedings.neurips.cc
Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the
rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets …
rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets …
Mm-bd: Post-training detection of backdoor attacks with arbitrary backdoor pattern types using a maximum margin statistic
Backdoor attacks are an important type of adversarial threat against deep neural network
classifiers, wherein test samples from one or more source classes will be (mis) classified to …
classifiers, wherein test samples from one or more source classes will be (mis) classified to …
Not all samples are born equal: Towards effective clean-label backdoor attacks
Recent studies demonstrated that deep neural networks (DNNs) are vulnerable to backdoor
attacks. The attacked model behaves normally on benign samples, while its predictions are …
attacks. The attacked model behaves normally on benign samples, while its predictions are …
Nearest is not dearest: Towards practical defense against quantization-conditioned backdoor attacks
Abstract Model quantization is widely used to compress and accelerate deep neural
networks. However recent studies have revealed the feasibility of weaponizing model …
networks. However recent studies have revealed the feasibility of weaponizing model …
Scale-up: An efficient black-box input-level backdoor detection via analyzing scaled prediction consistency
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries
embed a hidden backdoor trigger during the training process for malicious prediction …
embed a hidden backdoor trigger during the training process for malicious prediction …
Policycleanse: Backdoor detection and mitigation for competitive reinforcement learning
While real-world applications of reinforcement learning (RL) are becoming popular, the
security and robustness of RL systems are worthy of more attention and exploration. In …
security and robustness of RL systems are worthy of more attention and exploration. In …
Black-box dataset ownership verification via backdoor watermarking
Deep learning, especially deep neural networks (DNNs), has been widely and successfully
adopted in many critical applications for its high effectiveness and efficiency. The rapid …
adopted in many critical applications for its high effectiveness and efficiency. The rapid …