ReinforceBug: A Framework to Generate Adversarial Textual Examples
This work addresses the need for robust adversarial examples in deep learning, offering a framework that improves over prior methods, though it appears incremental in nature.
The authors tackled the problem of generating adversarial textual examples that preserve utility and are transferable across models, achieving a 10% higher success rate than TextFooler and maintaining 83.38% semantic similarity.
Adversarial Examples (AEs) generated by perturbing original training examples are useful in improving the robustness of Deep Learning (DL) based models. Most prior works, generate AEs that are either unconscionable due to lexical errors or semantically or functionally deviant from original examples. In this paper, we present ReinforceBug, a reinforcement learning framework, that learns a policy that is transferable on unseen datasets and generates utility-preserving and transferable (on other models) AEs. Our results show that our method is on average 10% more successful as compared to the state-of-the-art attack TextFooler. Moreover, the target models have on average 73.64% confidence in the wrong prediction, the generated AEs preserve the functional equivalence and semantic similarity (83.38% ) to their original counterparts, and are transferable on other models with an average success rate of 46%.