WaNet - Imperceptible Warping-based Backdoor Attack
With the thriving of deep learning and the widespread practice of using pre-trained networks, backdoor attacks have become an increasing security threat drawing many research interests in recent years. A third-party model can be poisoned in training to work well in normal conditions but behave maliciously when a trigger pattern appears. However, the existing backdoor attacks are all built on noise perturbation triggers, making them noticeable to humans. In this paper, we instead propose using warping-based triggers. The proposed backdoor outperforms the previous methods in a human inspection test by a wide margin, proving its stealthiness. To make such models undetectable by machine defenders, we propose a novel training mode, called the ``noise mode. The trained networks successfully attack and bypass the state of the art defense methods on standard classification datasets, including MNIST, CIFAR-10, and GTSRB. Behavior analyses show that our backdoors are transparent to network inspection, further proving this novel attack mechanism's efficiency.
Code (1)
Tasks
Backdoor AttackSimilar Papers 제목 키워드 기반
WaNet -- Imperceptible Warping-based Backdoor Attack
With the thriving of deep learning and the widespread practice of using pre-trained networks, backdoor attacks have become an increasing security threat drawing many research interests in recent years. A third-party mode…
Backdoor AttackAS-FIBA: Adaptive Selective Frequency-Injection for Backdoor Attack on Deep Face Restoration
Deep learning-based face restoration models, increasingly prevalent in smart devices, have become targets for sophisticated backdoor attacks. These attacks, through subtle trigger injection into input face images, can le…
Backdoor AttackTowards Imperceptible Backdoor Attack in Self-supervised Learning
Self-supervised learning models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in self-supervised learning often involve noticeable triggers, like colored patches, which are vulnerable t…
Backdoor AttackSelf-Supervised LearningInvisible Backdoor Attack against Self-supervised Learning
Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patches or visible noise, which are vulner…
Backdoor AttackSelf-Supervised LearningBackdoor Attack with Imperceptible Input and Latent Modification
Recent studies have shown that deep neural networks (DNN) are vulnerable to various adversarial attacks. In particular, an adversary can inject a stealthy backdoor into a model such that the compromised model will behave…
Backdoor Attack