Walking on the Edge: Fast, Low-Distortion Adversarial Examples
Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks in our everyday lives. When white-box attacks are almost always successful, it is typically only the distortion of the perturbations that matters in their evaluation. In this work, we argue that speed is important as well, especially when considering that fast attacks are required by adversarial training. Given more time, iterative methods can always find better solutions. We investigate this speed-distortion trade-off in some depth and introduce a new attack called boundary projection (BP) that improves upon existing methods by a large margin. Our key idea is that the classification boundary is a manifold in the image space: we therefore quickly reach the boundary and then optimize distortion on this manifold.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Imperceptible Adversarial Examples in the Physical World
Adversarial examples in the digital domain against deep learning-based computer vision models allow for perturbations that are imperceptible to human eyes. However, producing similar adversarial examples in the physical …
object-detectionObject DetectionEAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to adversarial examples - a visually indistinguishable adversarial image can easily be crafted to cause a well-trained model to misclassify…
Adversarial AttackAdversarial RobustnessReinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters
We present a Reinforcement Learning Platform for Adversarial Black-box untargeted and targeted attacks, RLAB, that allows users to select from various distortion filters to create adversarial examples. The platform uses …
image-classificationImage Classificationreinforcement-learningReinforcement LearningUnderstanding Catastrophic Overfitting in Single-step Adversarial Training
Although fast adversarial training has demonstrated both robustness and efficiency, the problem of "catastrophic overfitting" has been observed. This is a phenomenon in which, during single-step adversarial training, the…
Generating Structured Adversarial Attacks Using Frank-Wolfe Method
White box adversarial perturbations are generated via iterative optimization algorithms most often by minimizing an adversarial loss on a $\ell_p$ neighborhood of the original image, the so-called distortion set. Constra…
Adversarial Robustness