Neural Image Classifiers are effective but inherently hard to interpret and
susceptible to adversarial attacks. Solutions to both problems exist, among
others, in the form of counterfactual examples generation to enhance
explainability or adversarially augment training datasets for improved
robustness. However, existing methods exclusively address only one of the
issues. We propose a unified framework leveraging image-to-image translation
Generative Adversarial Networks (GANs) to produce counterfactual samples that
highlight salient regions for interpretability and act as adversarial samples
to augment the dataset for more robustness. This is achieved by combining the
classifier and discriminator into a single model that attributes real images to
their respective classes and flags generated images as "fake". We assess the
method's effectiveness by evaluating (i) the produced explainability masks on a
semantic segmentation task for concrete cracks and (ii) the model's resilience
against the Projected Gradient Descent (PGD) attack on a fruit defects
detection problem. Our produced saliency maps are highly descriptive, achieving
competitive IoU values compared to classical segmentation models despite being
trained exclusively on classification labels. Furthermore, the model exhibits
improved robustness to adversarial attacks, and we show how the discriminator's
"fakeness" value serves as an uncertainty measure of the predictions.

提出了一个统一框架，利用图像到图像转换生成对抗网络 (GANs) 生成对抗性样本，以增强可解释性，并扩充数据集以提高对抗性鲁棒性。该框架通过将分类器和辨别器结合成一个单一模型，将真实图像归类为相应的类别，并将生成的图像标记为 “伪造”，以实现这一目标。在具体裂缝的语义分割任务中，评估了方法的有效性，并在水果缺陷检测问题上评估了模型对投影梯度下降 (PGD) 攻击的鲁棒性。我们生成的显著性地图具有很高的描述性，尽管仅在分类标签上进行训练，但与传统分割模型相比，其竞争性 IoU 值表现。此外，该模型对抗性攻击的鲁棒性得到了改善，并展示了辨别器的 “伪造” 值作为预测的不确定性度量。