| In recent years, text generation tools utilizing Artificial Intelligence (AI) have occasionally been misused across various domains, such as generating student reports or creative writings. This issue prompts plagiarism detection services to enhance their capabilities in identifying AI-generated content. Adversarial attacks are often used to test the robustness of AI-generated text detectors. This work proposes a novel textual adversarial attack on detection models such as Fast-DetectGPT. The method employs embedding models for data perturbation, aiming at reconstructing the AI-generated texts to reduce the likelihood of detection of the true origin of the texts. Specifically, we employ different embedding techniques, including the Tsetlin Machine (TM), an interpretable approach in machine learning. By leveraging synonym-based perturbations guided by TM embeddings, our approach not only achieves competitive reductions in detection performance but also introduces interpretability into the adversarial attack process through the use of TM embeddings. |
*** Title, author list and abstract as submitted during Camera-Ready version delivery. Small changes that may have occurred during processing by Springer may not appear in this window.