| Title | Synonym-based Attack to Confuse Machine Learning Classifiers Using Black-box Setting |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Khan, Aasher, Rehman, Suriya, Khan, Muhammad U.S, Ali, Mazhar |
| Conference Name | 2019 4th International Conference on Emerging Trends in Engineering, Sciences and Technology (ICEEST) |
| Date Published | dec |
| Keywords | artificial intelligence, Black Box Security, black-box attack, black-box setting, Blogs, bot tweets, bots, composability, computer network security, convolutional neural network, cryptography, Deep Learning, deep learning classifiers, feature extraction, invasive software, learning (artificial intelligence), machine learning, machine learning algorithms, machine learning classifiers, Metrics, ML models, ML-based bot detection algorithms, ML-based models, pattern classification, popular content sharing platform, Predictive models, pubcrawl, resilience, Resiliency, social networking (online), supervised learning, synonym-based attack, Testing, Training, vulnerability constraints |
| Abstract | Twitter being the most popular content sharing platform is giving rise to automated accounts called "bots". Majority of the users on Twitter are bots. Various machine learning (ML) algorithms are designed to detect bots avoiding the vulnerability constraints of ML-based models. This paper contributes to exploit vulnerabilities of machine learning (ML) algorithms through black-box attack. An adversarial text sequence misclassifies the results of deep learning (DL) classifiers for bot detection. Literature shows that ML models are vulnerable to attacks. The aim of this paper is to compromise the accuracy of ML-based bot detection algorithms by replacing original words in tweets with their synonyms. Our results show 7.2% decrease in the accuracy for bot tweets, therefore classifying bot tweets as legitimate tweets. |
| DOI | 10.1109/ICEEST48626.2019.8981685 |
| Citation Key | khan_synonym-based_2019 |
Synonym-based Attack to Confuse Machine Learning Classifiers Using Black-box Setting