Evaluating Adversarial Robustness on Document Image Classification
Adversarial attacks and defenses have gained increasing interest on computer vision systems in recent years, but as of today, most investigations are limited to images. However, many artificial intelligence models actually handle documentary data, which is very different from real world images. Hence, in this work, we try to apply the adversarial attack philosophy on documentary and natural data and to protect models against such attacks. We focus our work on untargeted gradient-based, transfer-based and score-based attacks and evaluate the impact of adversarial training, JPEG input compression and grey-scale input transformation on the robustness of ResNet50 and EfficientNetB0 model architectures. To the best of our knowledge, no such work has been conducted by the community in order to study the impact of these attacks on the document image classification task.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackAdversarial RobustnessClassificationdocument-image-classificationDocument Image Classificationimage-classificationImage ClassificationPhilosophySimilar Papers 제목 키워드 기반
On Evaluating the Adversarial Robustness of Semantic Segmentation Models
Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been pr…
Adversarial Robustnessimage-classificationImage ClassificationImage Segmentation+1On Evaluating Adversarial Robustness of Chest X-ray Classification: Pitfalls and Best Practices
Vulnerability to adversarial attacks is a well-known weakness of Deep Neural Networks. While most of the studies focus on natural images with standardized benchmarks like ImageNet and CIFAR, little research has considere…
Adversarial RobustnessClassificationMedical DiagnosisX-ray ClassificationEvaluating Adversarial Robustness: A Comparison Of FGSM, Carlini-Wagner Attacks, And The Role of Distillation as Defense Mechanism
This technical report delves into an in-depth exploration of adversarial attacks specifically targeted at Deep Neural Networks (DNNs) utilized for image classification. The study also investigates defense mechanisms aime…
Adversarial Robustnessimage-classificationImage ClassificationSegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness
Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As o…
Adversarial AttackSegmentationSemantic SegmentationEvaluating Adversarial Robustness with Expected Viable Performance
We introduce a metric for evaluating the robustness of a classifier, with particular attention to adversarial perturbations, in terms of expected functionality with respect to possible adversarial perturbations. A classi…
Adversarial Robustness