Optimizing One-pixel Black-box Adversarial Attacks
The output of Deep Neural Networks (DNN) can be altered by a small perturbation of the input in a black box setting by making multiple calls to the DNN. However, the high computation and time required makes the existing approaches unusable. This work seeks to improve the One-pixel (few-pixel) black-box adversarial attacks to reduce the number of calls to the network under attack. The One-pixel attack uses a non-gradient optimization algorithm to find pixel-level perturbations under the constraint of a fixed number of pixels, which causes the network to predict the wrong label for a given image. We show through experimental results how the choice of the optimization algorithm and initial positions to search can reduce function calls and increase attack success significantly, making the attack more practical in real-world settings.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Superpixel Attack: Enhancing Black-box Adversarial Attack with Image-driven Division Areas
Deep learning models are used in safety-critical tasks such as automated driving and face recognition. However, small perturbations in the model input can significantly change the predictions. Adversarial attacks are use…
Adversarial AttackFace RecognitionPICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack
The studies on black-box adversarial attacks have become increasingly prevalent due to the intractable acquisition of the structural knowledge of deep neural networks (DNNs). However, the performance of emerging attacks …
Adversarial AttackBlack-box Adversarial Attacks with Bayesian Optimization
We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples using information limited to loss function evaluations of input-output pairs. We use Bayesian optimization~(BO) …
Bayesian OptimizationAmnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
It is well known that query-based attacks tend to have relatively higher success rates in adversarial black-box attacks. While research on black-box attacks is actively being conducted, relatively few studies have focuse…
image-classificationImage Classificationobject-detectionObject DetectionA Black-box Adversarial Attack Strategy with Adjustable Sparsity and Generalizability for Deep Image Classifiers
Constructing adversarial perturbations for deep neural networks is an important direction of research. Crafting image-dependent adversarial perturbations using white-box feedback has hitherto been the norm for such adver…
Adversarial Attack