During the outbreak of the COVID-19 pandemic, social networks became the preeminent medium for communication, social discussion, and entertainment. Social network users are regularly expressing their opinions about the impacts of the coronavirus pandemic. Therefore, social networks serve as a reliable source for studying the topics, emotions, and attitudes of users that have been discussed during the pandemic. In this paper, we investigate the reactions and attitudes of people towards topics raised on social media platforms. We collected data of two large-scale COVID-19 datasets from Twitter and Instagram for six and three months, respectively. This paper analyzes the reaction of social network users in terms of different aspects including sentiment analysis, topic detection, emotions, and the geo-temporal characteristics of our dataset. We show that the dominant sentiment reactions on social media are neutral, while the most discussed topics by social network users are about health issues. This paper examines the countries that attracted a higher number of posts and reactions from people, as well as the distribution of health-related topics discussed in the most mentioned countries. We shed light on the temporal shift of topics over countries. Our results show that posts from the top-mentioned countries influence and attract more reactions worldwide than posts from other parts of the world.

Deep learning methods have gained increasing attention in various applications due to their outstanding performance. For exploring how this high performance relates to the proper use of data artifacts and the accurate problem formulation of a given task, interpretation models have become a crucial component in developing deep learning-based systems. Interpretation models enable the understanding of the inner workings of deep learning models and offer a sense of security in detecting the misuse of artifacts in the input data. Similar to prediction models, interpretation models are also susceptible to adversarial inputs. This work introduces two attacks, AdvEdge and AdvEdge $^{+}$ , which deceive both the target deep learning model and the coupled interpretation model. We assess the effectiveness of proposed attacks against four deep learning model architectures coupled with four interpretation models that represent different categories of interpretation models. Our experiments include the implementation of attacks using various attack frameworks. We also explore the attack resilience against three general defense mechanisms and potential countermeasures. Our analysis shows the effectiveness of our attacks in terms of deceiving the deep learning models and their interpreters, and highlights insights to improve and circumvent the attacks.

Establishing trust and helping experts debug and understand the inner workings of deep learning models, interpretation methods are increasingly coupled with these models, building interpretable deep learning systems. However, adversarial attacks pose a significant threat to public trust by making interpretations of deep learning models confusing and difficult to understand. In this paper, we present a novel Single-class target-specific ADVersarial attack called SingleADV. The goal of SingleADV is to generate a universal perturbation that deceives the target model into confusing a specific category of objects with a target category while ensuring highly relevant and accurate interpretations. The universal perturbation is stochastically and iteratively optimized by minimizing the adversarial loss that is designed to consider both the classifier and interpreter costs in targeted and non-targeted categories. In this optimization framework, ruled by the first- and second-moment estimations, the desired loss surface promotes high confidence and interpretation scores of adversarial samples. By avoiding unintended misclassification of samples from other categories, SingleADV enables more effective targeted attacks on interpretable deep learning systems in both white-box and black-box scenarios. To evaluate the effectiveness of SingleADV, we conduct experiments using four different model architectures (ResNet-50, VGG-16, DenseNet-169, and Inception-V3) coupled with three interpretation models (CAM, Grad, and MASK). Through extensive empirical evaluation, we demonstrate that SingleADV effectively deceives target deep learning models and their associated interpreters under various conditions and settings. Our results show that the performance of SingleADV is effective, with an average attack success rate of 74% and prediction confidence exceeding 77% on successful adversarial samples. Furthermore, we discuss several countermeasures against SingleADV, including a transfer-based learning approach and existing preprocessing defenses.

Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and machine perception, text-based models have also fallen victim to these attacks. However, these attacks often fail to maintain the semantic meaning of the text and similarity. This paper introduces AdvChar, a black-box attack on Interpretable Natural Language Processing Systems, designed to mislead the classifier while keeping the interpretation similar to benign inputs, thus exploiting trust in system transparency. AdvChar achieves this by making less noticeable modifications to text input, forcing the deep learning classifier to make incorrect predictions and preserve the original interpretation. We use an interpretation-focused scoring approach to determine the most critical tokens that, when changed, can cause the classifier to misclassify the input. We apply simple character-level modifications to measure the importance of tokens, minimizing the difference between the original and new text while generating adversarial interpretations similar to benign ones. We thoroughly evaluated AdvChar by testing it against seven NLP models and three interpretation models using benchmark datasets for the classification task. Our experiments show that AdvChar can significantly reduce the prediction accuracy of current deep learning models by altering just two characters on average in input samples.