Enhancing Robustness of Machine Learning Algorithms for Bangla Text Classification: A Defensive Approach against Adversarial Attacks

Machine learning algorithms have gained popularity for performing numerous tasks on text data including, prediction, recommendation, sentiment analysis, etc. Along with the development of these algorithms, several adversarial attacks have emerged that can be injected into input data to manipulate the outputs of machine learning-based models. These attacks affect the models’ performance hence leading to generating incorrect results. This paper introduces two Evasion-type adversarial machine-learning attacks for Bangla text and later proposes defensive mechanisms against them. At first, a comprehensive Bangla dataset has been generated and a teacher model is trained on that. Then the introduced attacks are injected into the dataset to manipulate it. Alongside this, a student model is trained on the manipulated dataset to build a robust model that learns to defeat any future adversarial attack. Finally, the experimental analysis shows that the proposed framework achieves robustness and can defeat adversarial machine-learning attacks for Bangla text.