destroR: Attacking Transfer Models with Obfuscous Examples to Discard Perplexity

TL;DR

This paper introduces destroR, a novel adversarial attack method that generates ambiguous, obfuscous examples in multiple languages to challenge and evaluate the robustness of state-of-the-art NLP models.

Contribution

It presents a new attack strategy that creates high-perplexity adversarial inputs, including for Bangla, to test and improve model robustness against obfuscous examples.

Findings

Successfully generated high-perplexity adversarial examples

Demonstrated vulnerability of models to obfuscous inputs

Included Bangla language in adversarial attack scenarios

Abstract

Advancements in Machine Learning & Neural Networks in recent years have led to widespread implementations of Natural Language Processing across a variety of fields with remarkable success, solving a wide range of complicated problems. However, recent research has shown that machine learning models may be vulnerable in a number of ways, putting both the models and the systems theyre used in at risk. In this paper, we intend to analyze and experiment with the best of existing adversarial attack recipes and create new ones. We concentrated on developing a novel adversarial attack strategy on current state-of-the-art machine learning models by producing ambiguous inputs for the models to confound them and then constructing the path to the future development of the robustness of the models. We will develop adversarial instances with maximum perplexity, utilizing machine learning and deep learning approaches in order to trick the models. In our attack recipe, we will analyze several datasets and focus on creating obfuscous adversary examples to put the models in a state of perplexity, and by including the Bangla Language in the field of adversarial attacks. We strictly uphold utility usage reduction and efficiency throughout our work.