2023 · 27 citations · 19 references
ComputingComputer ScienceCybersecurityComputer SecurityComputer VisionMachine LearningAdversary TechniquesDeep LearningAdversarial RobustnessBackdoor TechniquesMachine-learning AttacksTrainingTransformationsTrigger MechanismsTriggers
Deep neural networks (DNNs) are vulnerable to backdoor attacks. The backdoor adversaries intend to maliciously control the predictions of attacked DNNs by injecting hidden backdoors that can be activated by adversary-specified trigger patterns during the training process. One recent research revealed that most of the existing attacks failed in the real physical world since the trigger contained in the digitized test samples may be different from that of the one used for training. Accordingly, users can adopt spatial transformations as the image pre-processing to deactivate hidden backdoors. In this paper, we explore the previous findings from another side. We exploit classical spatial transformations (i.e., rotation and translation) with the specific parameter as trigger patterns to design a simple yet effective poisoning-based backdoor attack. For example, only images rotated to a particular angle can activate the embedded backdoor of attacked DNNs. Extensive experiments are conducted, verifying the effectiveness of our attack under both digital and physical settings and its resistance to existing backdoor defenses.
19
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
Bolun Wang, Yuanshun Yao, Shawn Shan et al. · 2019 · 1.3K citations · Full text
BadNets: Evaluating Backdooring Attacks on Deep Neural Networks
Tianyu Gu, Kang Liu, Brendan Dolan-Gavitt et al. · IEEE Access · 2019 · 1.1K citations · Full text
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
Xinyun Chen, Chang Liu, Bo Li et al. · arXiv (Cornell University) · 2017 · 1K citations · Full text