Adversarial Attacks against Deep Saliency Models
Currently, a plethora of saliency models based on deep neural networks have led great breakthroughs in many complex high-level vision tasks (e.g. scene description, object detection). The robustness of these models, however, has not yet been studied. In this paper, we propose a sparse feature-space adversarial attack method against deep saliency models for the first time. The proposed attack only requires a part of the model information, and is able to generate a sparser and more insidious adversarial perturbation, compared to traditional image-space attacks. These adversarial perturbations are so subtle that a human observer cannot notice their presences, but the model outputs will be revolutionized. This phenomenon raises security threats to deep saliency models in practical applications. We also explore some intriguing properties of the feature-space attack, e.g. 1) the hidden layers with bigger receptive fields generate sparser perturbations, 2) the deeper hidden layers achieve higher attack success rates, and 3) different loss functions and different attacked layers will result in diverse perturbations. Experiments indicate that the proposed method is able to successfully attack different model architectures across various image scenes.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial Attackobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Deep neural network loses attention to adversarial images
Adversarial algorithms have shown to be effective against neural networks for a variety of tasks. Some adversarial algorithms perturb all the pixels in the image minimally for the image classification task in image class…
image-classificationImage ClassificationSAD: Saliency-based Defenses Against Adversarial Examples
With the rise in popularity of machine and deep learning models, there is an increased focus on their vulnerability to malicious inputs. These adversarial examples drift model predictions away from the original intent of…
Adversarial AttackMusic Genre RecognitionDoes Saliency-Based Training bring Robustness for Deep Neural Networks in Image Classification?
Deep Neural Networks are powerful tools to understand complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. While online saliency-guided training…
image-classificationImage ClassificationDetection Defense Against Adversarial Attacks with Saliency Map
It is well established that neural networks are vulnerable to adversarial examples, which are almost imperceptible on human vision and can cause the deep models misbehave. Such phenomenon may lead to severely inestimable…
Model-based Saliency for the Detection of Adversarial Examples
Adversarial perturbations cause a shift in the salient features of an image, which may result in a misclassification. We demonstrate that gradient-based saliency approaches are unable to capture this shift, and develop a…