Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink
Though it is well known that the performance of deep neural networks (DNNs) degrades under certain light conditions, there exists no study on the threats of light beams emitted from some physical source as adversarial attacker on DNNs in a real-world scenario. In this work, we show by simply using a laser beam that DNNs are easily fooled. To this end, we propose a novel attack method called Adversarial Laser Beam ($AdvLB$), which enables manipulation of laser beam's physical parameters to perform adversarial attack. Experiments demonstrate the effectiveness of our proposed approach in both digital- and physical-settings. We further empirically analyze the evaluation results and reveal that the proposed laser beam attack may lead to some interesting prediction errors of the state-of-the-art DNNs. We envisage that the proposed $AdvLB$ method enriches the current family of adversarial attacks and builds the foundation for future robustness studies for light.
Code (1)
Tasks
Adversarial AttackSimilar Papers 제목 키워드 기반
Adversarial Neon Beam: A Light-based Physical Attack to DNNs
In the physical world, deep neural networks (DNNs) are impacted by light and shadow, which can have a significant effect on their performance. While stickers have traditionally been used as perturbations in most physical…
Adversarial AttackShadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon
Estimating the risk level of adversarial examples is essential for safely deploying machine learning models in the real world. One popular approach for physical-world attacks is to adopt the "sticker-pasting" strategy, w…
Adversarial AttackTraffic Sign RecognitionvalidAdversarial Wear and Tear: Exploiting Natural Damage for Generating Physical-World Adversarial Examples
The presence of adversarial examples in the physical world poses significant challenges to the deployment of Deep Neural Networks in safety-critical applications such as autonomous driving. Most existing methods for craf…
Autonomous DrivingImage-to-Image TranslationUnsupervised Image-To-Image TranslationAdversarial Catoptric Light: An Effective, Stealthy and Robust Physical-World Attack to DNNs
Deep neural networks (DNNs) have demonstrated exceptional success across various tasks, underscoring the need to evaluate the robustness of advanced DNNs. However, traditional methods using stickers as physical perturbat…
Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs
Most existing deep neural networks (DNNs) are easily disturbed by slight noise. However, there are few researches on physical attacks by deploying lighting equipment. The light-based physical attacks has excellent covert…
Adversarial Attack